© 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. 55152
    Prev
    Next
    INDEX
    Explanations

    case where situation

    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
    å¾ħ人
    -0.07
    ä¹Ķæľ¨
    -0.06
    Ỽt
    -0.06
    .copy
    -0.06
    onge
    -0.06
    ãĥŃãĥ¼ãĥī
    -0.06
    åĪ¤
    -0.06
    å¢ŀéķ¿éĢŁåº¦
    -0.06
    çݯ路
    -0.06
     techniques
    -0.06
    POSITIVE LOGITS
    ãĤĴ表
    0.08
     messy
    0.08
    mbH
    0.08
    é¼ĵ
    0.08
    åĨĻåĩº
    0.07
    åĨĻæĪIJ
    0.07
    ingar
    0.07
    à¸Łà¸Ńรà¹Įม
    0.07
    _dark
    0.07
     specifics
    0.07
    Activations Density 0.002%

    No Known Activations