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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63196
    Prev
    Next
    INDEX
    Explanations

    SELECT Karen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.07
    ably
    -0.06
    ãģ¾ãģĹãģ¦
    -0.06
     vX
    -0.06
    <\/
    -0.06
    波波
    -0.06
    lu
    -0.06
    able
    -0.06
    æºIJèĩª
    -0.06
    >@
    -0.06
    POSITIVE LOGITS
    liÄį
    0.08
    pies
    0.07
    esser
    0.07
    agina
    0.07
    ÙĬرÙĬØ©
    0.07
    _stock
    0.07
    åIJīæĸ¯
    0.07
     Cát
    0.07
    apak
    0.07
    åĸľæĢĴåĵĢ
    0.07
    Activations Density 0.181%

    No Known Activations