© 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. 20082
    Prev
    Next
    INDEX
    Explanations

    import 'from'

    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
    gtest
    -0.08
    涯
    -0.08
     Stazione
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    jerne
    -0.07
    aghan
    -0.07
    .perform
    -0.07
    اÙĨات
    -0.07
    assar
    -0.07
    undry
    -0.07
    POSITIVE LOGITS
    .;
    0.08
    nj
    0.07
    ç«£
    0.07
    verts
    0.06
    ks
    0.06
    aja
    0.06
    aj
    0.06
     {};
    0.06
    ajah
    0.06
    yu
    0.06
    Activations Density 0.082%

    No Known Activations