© 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. 64698
    Prev
    Next
    INDEX
    Explanations

    position, measurement, and display

    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
     خز
    -0.08
     nowadays
    -0.08
    åIJĪçIJĨåĮĸ
    -0.07
    andung
    -0.07
    è°±åĨĻ
    -0.07
    ãĤŃãĥ¥ãĥ¼
    -0.07
    ç¿»äºĨ
    -0.07
    delen
    -0.07
    udur
    -0.07
    _Params
    -0.07
    POSITIVE LOGITS
    record
    0.07
    è°ĥæķ´
    0.07
     recording
    0.07
    è®°å½ķä¸ĭ
    0.07
    åŁºåĩĨ
    0.07
    ä¸ī次
    0.07
    ä¾Ŀ次
    0.07
    mark
    0.07
    itsu
    0.07
    åĸĥ
    0.07
    Activations Density 0.020%

    No Known Activations