© 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. 4858
    Prev
    Next
    INDEX
    Explanations

    end of month

    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
     ê²ĥìĿ´ê³ł
    -0.09
    tria
    -0.08
    enang
    -0.07
     TObject
    -0.07
    ãĢįãĢģãĢĮ
    -0.07
    $/,
    -0.07
    worm
    -0.07
    èĢĮæĺ¯åľ¨
    -0.07
    ario
    -0.07
    :],
    -0.07
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½
    0.10
    çŃīçŃī
    0.08
     enfin
    0.07
    è¿ĻäºĽåĽłç´ł
    0.07
    以ä¸Ĭ
    0.07
    è¿ĻäºĽéĥ½æĺ¯
    0.07
    以ä¸Ĭæĺ¯
    0.06
     importantly
    0.06
    ä¸Ģæ°Ķ
    0.06
    èĭ¥ä¸įæĺ¯
    0.06
    Activations Density 0.201%

    No Known Activations