© 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. 58327
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operators

    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
    æľŃ
    -0.08
    åı¯åIJ¦
    -0.07
    orne
    -0.07
    éĩįå·¥
    -0.07
    cliffe
    -0.07
    olland
    -0.07
     Scrolls
    -0.07
    ç½ijéĢļ
    -0.07
    ModelIndex
    -0.07
    .Annotations
    -0.07
    POSITIVE LOGITS
    ighton
    0.07
    æ¥ł
    0.07
    igno
    0.06
    æl
    0.06
    รà¹Į
    0.06
    ç¯ī
    0.06
    ohana
    0.06
    ç¹Ķ
    0.06
    tou
    0.06
    ight
    0.06
    Activations Density 0.002%

    No Known Activations