© 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. 70166
    Prev
    Next
    INDEX
    Explanations

    Non-English language

    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
    _MUTEX
    -0.08
     siege
    -0.07
    issy
    -0.07
     Radar
    -0.07
     thầy
    -0.07
     coz
    -0.07
     Cần
    -0.07
     consolidate
    -0.06
    getTitle
    -0.06
    cate
    -0.06
    POSITIVE LOGITS
    不由得
    0.07
    锄
    0.07
    し�
    0.07
    rolling
    0.06
    owing
    0.06
    ,last
    0.06
     %{
    0.06
    .LoggerFactory
    0.06
    逐年
    0.06
     inexp
    0.06
    Activations Density 0.087%

    No Known Activations