© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7302
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and problem solving

    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
    å½ĵåľ°æŶéĹ´
    -0.07
    enius
    -0.07
    å¢ĥå¤ĸè¾ĵåħ¥
    -0.07
     locals
    -0.07
     plen
    -0.07
     neutrality
    -0.07
    åľ¨å½ĵåľ°
    -0.07
    Ļ
    -0.07
     locality
    -0.07
    åIJī
    -0.07
    POSITIVE LOGITS
    æķ°åĪĹ
    0.08
     Guerrero
    0.07
    /item
    0.07
    ologe
    0.07
    åĤ¨çī©
    0.07
    çª
    0.07
    çłĶ究对象
    0.07
    ä¸į好æĦıæĢĿ
    0.06
    _der
    0.06
    OTION
    0.06
    Activations Density 0.003%

    No Known Activations