Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 86150
    Prev
    Next
    INDEX
    Explanations

    Medical symptoms

    np_max-act · gemini-2.0-flash

    first-person patient reports of bodily symptoms—especially pain and abnormal sensations—localized to specific body parts with timing/severity details.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    first-person descriptions of bodily symptoms localized to specific body parts, especially reports of pain or abnormal sensations and their onset or progression.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dashes
    -0.07
     pump
    -0.07
    这次
    -0.07
     returns
    -0.07
     Newsletter
    -0.07
     tn
    -0.06
     demands
    -0.06
     trig
    -0.06
     stakes
    -0.06
     EF
    -0.06
    POSITIVE LOGITS
    пущен
    0.08
    Bindable
    0.07
    ellular
    0.07
     Sexy
    0.07
    udent
    0.07
     regenerate
    0.07
     مجال
    0.07
     {}\
    0.07
    Strong
    0.07
    /tool
    0.07
    Activations Density 0.066%

    No Known Activations