© 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. 59951
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by parentheses

    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
    åĪĽä¼ĺ
    -0.08
    oves
    -0.07
    embro
    -0.07
    éĩijèŀįè¡Įä¸ļ
    -0.07
    aded
    -0.07
    åIJijèį£
    -0.07
    ëĤ´
    -0.07
    olut
    -0.07
    åŃ¦å¹´åº¦
    -0.07
    overs
    -0.07
    POSITIVE LOGITS
     hazard
    0.06
     tap
    0.06
    stal
    0.06
     Dial
    0.06
    quat
    0.06
    åıªä¸įè¿ĩ
    0.06
     dock
    0.06
     Sera
    0.06
    åĶĨ
    0.06
     Tent
    0.06
    Activations Density 0.577%

    No Known Activations