© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61966
    Prev
    Next
    INDEX
    Explanations

    email address

    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
    æĽ³
    -0.07
    ằn
    -0.07
     abr
    -0.07
    bout
    -0.07
    -selector
    -0.07
    _counters
    -0.06
    ëł¥ìĿ´
    -0.06
    ColumnType
    -0.06
    umin
    -0.06
     Elli
    -0.06
    POSITIVE LOGITS
    ubile
    0.07
    inde
    0.07
    ียà¸Ļ
    0.07
    ç¡®
    0.07
    º
    0.06
    æľ¬æ³ķ
    0.06
    åŃĺæľī
    0.06
    åŀĴ
    0.06
    midt
    0.06
    gni
    0.06
    Activations Density 0.208%

    No Known Activations