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. 19-RESID-POST-AA
    6. 129767
    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
    án
    -0.07
     saja
    -0.07
    orta
    -0.07
    лись
    -0.07
    ged
    -0.06
     		↵
    -0.06
     adjective
    -0.06
    ária
    -0.06
    ría
    -0.06
     yet
    -0.06
    POSITIVE LOGITS
     juicy
    0.07
     полов
    0.07
    עצמאי
    0.07
    Civil
    0.07
    oid
    0.06
    绐
    0.06
    western
    0.06
    /,↵
    0.06
    VectorXd
    0.06
    Equivalent
    0.06
    Activations Density 0.005%

    No Known Activations