© 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. 21439
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with frac

    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
     chance
    -0.07
    æĤł
    -0.06
     setattr
    -0.06
     fre
    -0.06
    utt
    -0.06
    åīįç¨ĭ
    -0.06
    峡
    -0.06
    ä¸Ģ寸
    -0.06
    uvia
    -0.06
    æ´ŀ
    -0.06
    POSITIVE LOGITS
    иÑĤелÑĮÑģÑĤва
    0.08
     EITHER
    0.08
     ${({
    0.07
    ibri
    0.07
    å¤§æľ¬
    0.07
     Kasat
    0.07
    noz
    0.07
    иÑĤелÑĮÑģÑĤво
    0.07
    RU
    0.07
     Tua
    0.07
    Activations Density 0.003%

    No Known Activations