© 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. 58960
    Prev
    Next
    INDEX
    Explanations

    make make a callbetween the twowhere where userlearn to learnget get and timeanalyst analyst Joerun runMyfunctionusing using heralso also beyour company

    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
    Negative Logits
    pill
    -0.08
    plant
    -0.08
     ('\
    -0.07
    ÄĽn
    -0.07
    archy
    -0.07
    oi
    -0.07
    Ð¢Ðł
    -0.07
    inei
    -0.07
    alak
    -0.07
    duino
    -0.07
    POSITIVE LOGITS
    %A
    0.07
    ãĢģãĢģ
    0.07
    ãĢģãĢģãĢģ
    0.07
    éģIJ
    0.07
    åĵ¥
    0.06
    achs
    0.06
    ,,,,,,,,
    0.06
     Volta
    0.06
    åł¤
    0.06
    dien
    0.06
    Activations Density 1.164%

    No Known Activations