© 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. 44165
    Prev
    Next
    INDEX
    Explanations

    secondary lesser additional

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çİĭ家
    -0.07
    راز
    -0.07
    aec
    -0.07
    æŃ£å¥½
    -0.07
    rup
    -0.07
    夫åIJĽ
    -0.07
    æľĢæĸ°æĸĩç«ł
    -0.06
     Ria
    -0.06
    lungs
    -0.06
    sing
    -0.06
    POSITIVE LOGITS
    次è¦ģ
    0.10
     secondary
    0.10
     lesser
    0.10
    æł¹æį®éľĢè¦ģ
    0.10
    secondary
    0.09
    ä¾Ŀ次为
    0.09
     additional
    0.09
    Secondary
    0.08
     optionally
    0.08
     Lesser
    0.08
    Activations Density 0.138%

    No Known Activations