© 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. 21207
    Prev
    Next
    INDEX
    Explanations

    your

    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
    热度
    -0.07
    aption
    -0.07
    /mol
    -0.07
    椪
    -0.07
    (rowIndex
    -0.06
     yönel
    -0.06
    跬
    -0.06
    ϳ
    -0.06
    Solution
    -0.06
    鞯
    -0.06
    POSITIVE LOGITS
     timed
    0.08
     Chap
    0.08
    Objects
    0.07
    同一
    0.07
     fos
    0.07
    转动
    0.07
    ibernate
    0.07
    _week
    0.07
    野生
    0.07
    اجتماع
    0.07
    Activations Density 0.031%

    No Known Activations