© 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. 27957
    Prev
    Next
    INDEX
    Explanations

    `/filepath` or `+xml`

    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
    asser
    -0.06
    azzi
    -0.06
    aliza
    -0.06
    asal
    -0.06
    éĨĴ
    -0.06
    alah
    -0.06
    agni
    -0.06
     '::
    -0.06
    è½¼
    -0.06
    aze
    -0.06
    POSITIVE LOGITS
    /filepath
    0.08
    æĽ
    0.08
    +xml
    0.08
    reté
    0.08
    urations
    0.08
    aderos
    0.07
    æİĥ
    0.07
    -football
    0.07
    æ¡ĥæĿİ
    0.07
    gad
    0.07
    Activations Density 0.017%

    No Known Activations