© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    file path components

    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
    imate
    -0.07
    _easy
    -0.07
    /WebAPI
    -0.06
    ritz
    -0.06
     Helf
    -0.06
    indust
    -0.06
    æĵįä½ľ
    -0.06
    æł·
    -0.06
    lingen
    -0.06
     másc
    -0.06
    POSITIVE LOGITS
    .Loader
    0.08
    å®īåħ¨é£İéĻ©
    0.07
    winkel
    0.07
    Compat
    0.07
    à¸Ľà¸£à¸´
    0.07
    ãĥĹãĥªãĥ³
    0.07
    åĭīåĬ±
    0.07
    etten
    0.07
    asmus
    0.07
    inch
    0.07
    Activations Density 0.144%

    No Known Activations