© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 80409
    Prev
    Next
    INDEX
    Explanations

    overturn

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    窗帘
    -0.08
    acos
    -0.08
    _rule
    -0.08
    Foo
    -0.07
     Stops
    -0.07
    轮融资
    -0.07
    忽视
    -0.07
    -find
    -0.07
    _MENU
    -0.07
    寇
    -0.07
    POSITIVE LOGITS
    �
    0.08
    ള
    0.07
    maktad
    0.07
     overturn
    0.07
     перев
    0.07
    氰
    0.07
     międ
    0.07
     rotational
    0.07
     מק
    0.07
     (+
    0.07
    Activations Density 0.001%

    No Known Activations