© 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. 11-RESID-POST-AA
    11. 23451
    Prev
    Next
    INDEX
    Explanations

    code

    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
     refute
    -0.07
     offic
    -0.07
    给人
    -0.07
     näm
    -0.07
     å
    -0.06
     öner
    -0.06
    lig
    -0.06
     sư
    -0.06
    指導
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    '$
    0.07
    上年同期
    0.07
    /**↵
    0.07
    分布在
    0.07
    Զ
    0.07
    main
    0.07
    公开发行
    0.07
    .Modules
    0.07
    QString
    0.07
    פגישה
    0.07
    Activations Density 0.091%

    No Known Activations