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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 21768
    Prev
    Next
    INDEX
    Explanations

    house

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     xuân
    -0.07
    动摇
    -0.07
    شاه
    -0.07
    来的
    -0.07
    &)↵
    -0.07
    esteem
    -0.06
     وغيرها
    -0.06
    恼
    -0.06
     Já
    -0.06
    刹
    -0.06
    POSITIVE LOGITS
     директор
    0.08
     wizard
    0.07
    (st
    0.07
     sil
    0.07
    的城市
    0.07
    /topic
    0.07
     nuclear
    0.07
    结束了
    0.06
     INTEGER
    0.06
     indirect
    0.06
    Activations Density 0.000%

    No Known Activations