© 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
    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. 21174
    Prev
    Next
    INDEX
    Explanations

    of

    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
    揮
    -0.06
    女神
    -0.06
    妃
    -0.06
    大使
    -0.06
     이미
    -0.06
     submodule
    -0.06
    批准
    -0.06
    _*
    -0.06
    士兵
    -0.06
    gó
    -0.06
    POSITIVE LOGITS
    _attach
    0.08
     bondage
    0.07
     Colour
    0.07
    /signup
    0.07
    GENERAL
    0.07
    .tools
    0.07
    thead
    0.07
     chez
    0.07
     clang
    0.07
    UIScreen
    0.07
    Activations Density 0.073%

    No Known Activations