© 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. 33142
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
    ัà¸Ķ
    -0.08
    /lg
    -0.08
    åIJĮåŃ¦åľ¨
    -0.07
    ivamente
    -0.07
    /]
    -0.07
    .cleanup
    -0.07
    夫åIJĽ
    -0.07
    __/
    -0.07
    _DIRECT
    -0.07
    _suite
    -0.07
    POSITIVE LOGITS
    зде
    0.07
    utor
    0.07
    ari
    0.07
    igma
    0.07
    _guess
    0.07
    æ²»çIJĨ
    0.07
    illing
    0.07
    碧
    0.07
    aven
    0.07
    eda
    0.07
    Activations Density 0.099%

    No Known Activations