© 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. 552
    Prev
    Next
    INDEX
    Explanations

    football coach or player

    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
    æ£ĢæŁ¥å·¥ä½ľ
    -0.08
    çĸ¯
    -0.07
    swire
    -0.07
    éĶ¦æ±Ł
    -0.07
    ä¸įèĭŁ
    -0.07
     spoj
    -0.07
    ì°°
    -0.07
    otty
    -0.07
    åįļçĪ±
    -0.07
    åIJ¬äºĨ
    -0.07
    POSITIVE LOGITS
    alice
    0.07
    itzen
    0.07
    ÙİعÙĴ
    0.06
    æĦıåij³
    0.06
    vat
    0.06
    èѦæĪĴ
    0.06
    [table
    0.06
    (hand
    0.06
    mlin
    0.06
    callable
    0.06
    Activations Density 0.005%

    No Known Activations