© 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. 13769
    Prev
    Next
    INDEX
    Explanations

    Call Us, See Movie, See Details

    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
    arts
    -0.07
    æŀ£
    -0.07
     held
    -0.07
    Zo
    -0.06
     virtually
    -0.06
    Eval
    -0.06
     fran
    -0.06
    ipp
    -0.06
    èį
    -0.06
    ->
    -0.06
    POSITIVE LOGITS
    ebol
    0.08
    ,axis
    0.08
    fiz
    0.08
    SSIP
    0.08
    chet
    0.08
    /gif
    0.07
    æħİ
    0.07
     DOUBLE
    0.07
    ungnya
    0.07
    -framework
    0.07
    Activations Density 0.002%

    No Known Activations