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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 130907
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وال
    -0.08
     disastrous
    -0.07
    (unsigned
    -0.07
    不幸
    -0.06
    疑
    -0.06
    oru
    -0.06
     поряд
    -0.06
    —
    -0.06
    being
    -0.06
    DataRow
    -0.06
    POSITIVE LOGITS
    气质
    0.07
    ဘ
    0.07
    (Job
    0.07
    雕刻
    0.07
    addField
    0.07
    gregator
    0.07
    (Mat
    0.07
     collector
    0.07
    鬓
    0.07
    _initial
    0.07
    Activations Density 0.134%

    No Known Activations