© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 8359
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    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
    acco
    -0.07
    -car
    -0.07
    ayar
    -0.07
    微商
    -0.07
    꿴
    -0.07
    .btnDelete
    -0.07
    卿
    -0.06
    购车
    -0.06
    半个月
    -0.06
    转入
    -0.06
    POSITIVE LOGITS
    aturing
    0.08
     Summer
    0.07
     Bowl
    0.07
    (ast
    0.07
     rug
    0.07
    فو
    0.07
     bất
    0.07
    值得
    0.07
    MZ
    0.06
     Streaming
    0.06
    Activations Density 0.014%

    No Known Activations