© 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. 4602
    Prev
    Next
    INDEX
    Explanations

    physics and engineering terms

    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
    æīĢåľ¨
    -0.08
    ós
    -0.08
    åĴĮçłĶ究
    -0.07
    ãģ¼ãģĨ
    -0.06
    ëĮĢë¡ľ
    -0.06
    åIJİéĢĢ
    -0.06
    æĸĽ
    -0.06
    çĽ¼
    -0.06
    å¿ħè¦ģæŶ
    -0.06
    èĭ¦å¿ĥ
    -0.06
    POSITIVE LOGITS
    pend
    0.07
    йл
    0.07
    HITE
    0.07
    .intro
    0.07
    imension
    0.07
    ondon
    0.07
    anging
    0.07
    amak
    0.07
    å¼ı设计
    0.07
    _live
    0.07
    Activations Density 0.033%

    No Known Activations