© 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. 4750
    Prev
    Next
    INDEX
    Explanations

    unless, only, exceptions

    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
     especially
    -0.07
    以å¤ĸãģ«ãĤĤ
    -0.07
    ild
    -0.06
     Especially
    -0.06
    arel
    -0.06
    æĬ¬å¤´
    -0.06
    쿨
    -0.06
     pula
    -0.06
    æĮļ
    -0.06
    ivain
    -0.06
    POSITIVE LOGITS
    imits
    0.08
     ÑĢазве
    0.08
    æŀģ为
    0.08
    atat
    0.08
    é¡į
    0.07
    æł¹æľ¬å°±æĺ¯
    0.07
    ä¹Ŀéĩį
    0.07
    ewis
    0.07
    anka
    0.07
    å¾·æĭī
    0.07
    Activations Density 0.101%

    No Known Activations