© 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. 26634
    Prev
    Next
    INDEX
    Explanations

    realtime unit, splitting, attitude, command, function, Hazem, social, sentences, Opening, creating

    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
    Schedulers
    -0.09
    kee
    -0.09
    ocre
    -0.08
    odesk
    -0.08
    Reducers
    -0.08
    ,www
    -0.08
    .bundle
    -0.08
    witz
    -0.08
     беÑģпла
    -0.08
    AllWindows
    -0.08
    POSITIVE LOGITS
    ix
    0.08
     specifically
    0.07
    ing
    0.06
    $
    0.06
     specific
    0.06
    æݨ
    0.06
    ularity
    0.06
    b
    0.06
    ES
    0.06
    ul
    0.06
    Activations Density 0.001%

    No Known Activations