© 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. 4576
    Prev
    Next
    INDEX
    Explanations

    ATPase

    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
    以轻
    -0.08
    ια
    -0.08
    маÑģ
    -0.08
    kker
    -0.07
    .testing
    -0.07
    ÐĺÐIJ
    -0.07
     guida
    -0.07
    bruch
    -0.07
    swick
    -0.07
    è·¯è¿ĩ
    -0.07
    POSITIVE LOGITS
     ATP
    0.08
    -powered
    0.08
    驱åĬ¨çļĦ
    0.07
    oppable
    0.07
    å¥
    0.07
    æľĢä¼Łå¤§çļĦ
    0.07
    sep
    0.07
     Herc
    0.07
    为å¸Ī
    0.07
    -driven
    0.07
    Activations Density 0.033%

    No Known Activations