© 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. 531
    Prev
    Next
    INDEX
    Explanations

    importance of

    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
    interess
    -0.08
    umpa
    -0.08
    èij©
    -0.08
    ç¾ŀ涩
    -0.08
    วà¹Īาà¹Ħà¸Ķà¹ī
    -0.07
    æ¯Ķè¾ĥä½İ
    -0.07
     characteristic
    -0.07
    æĽ´æİ¥è¿ij
    -0.07
    æ¯Ķè¾ĥç®Ģåįķ
    -0.07
    éĢ²å±ķ
    -0.07
    POSITIVE LOGITS
    çļĦéĩįè¦ģæĢ§
    0.13
     importance
    0.13
    éĩįè¦ģæĢ§
    0.13
     Importance
    0.12
    å¿ħè¦ģæĢ§
    0.11
    importance
    0.10
     benefits
    0.10
    /import
    0.10
     pentingnya
    0.10
    ÙĩÙħÙĬØ©
    0.10
    Activations Density 0.132%

    No Known Activations