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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 16459
    Prev
    Next
    INDEX
    Explanations

    °C

    np_max-act · gemini-2.0-flash
    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
     pym
    -0.07
    icaid
    -0.07
     params
    -0.07
    غضب
    -0.07
    ธนาคาร
    -0.06
    特朗
    -0.06
    杲
    -0.06
    промышленн
    -0.06
     utan
    -0.06
     вып
    -0.06
    POSITIVE LOGITS
    меча
    0.08
    .market
    0.07
    萼
    0.07
     opposed
    0.06
     Lahore
    0.06
     второй
    0.06
    𝕣
    0.06
     chronic
    0.06
    Lemma
    0.06
    的女儿
    0.06
    Activations Density 0.002%

    No Known Activations