© 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. 44967
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and symbols

    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
    ä¸Ģéĥİ
    -0.07
    atters
    -0.07
    atter
    -0.06
    æĺ¯ä¸ĢéŨ
    -0.06
    _VARS
    -0.06
    éĺħ
    -0.06
    æĪĸåħ¶å®ĥ
    -0.06
     Diss
    -0.06
    à¦Ľ
    -0.06
    ç¨ĭ度çļĦ
    -0.06
    POSITIVE LOGITS
    Converter
    0.08
    osan
    0.08
    _conversion
    0.07
    .allowed
    0.07
    ingang
    0.07
    åĩºåįĸ
    0.07
    转æį¢åĻ¨
    0.07
    åħ´å®ī
    0.07
    omit
    0.07
    ิà¹īว
    0.07
    Activations Density 0.006%

    No Known Activations