© 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. 15-RESID-POST-AA
    11. 23826
    Prev
    Next
    INDEX
    Explanations

    Dates and centuries

    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
    批示
    -0.08
    ome
    -0.08
    和支持
    -0.08
     totalTime
    -0.07
    "profile
    -0.07
    不少人
    -0.07
    爱好
    -0.07
    Popover
    -0.07
    みんな
    -0.07
    認為
    -0.07
    POSITIVE LOGITS
    HOUSE
    0.06
    );
↵
    0.06
    أسواق
    0.06
     Standard
    0.06
    金属
    0.06
     genetic
    0.06
    ,E
    0.06
    _/
    0.06
    );↵
    0.06
    */
    0.06
    Activations Density 0.197%

    No Known Activations