© 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. 34993
    Prev
    Next
    INDEX
    Explanations

    legal or technical 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
    Negative Logits
    (IB
    -0.07
    sv
    -0.07
     ï½ľ
    -0.06
    å·´å·´
    -0.06
    oe
    -0.06
    çݺ
    -0.06
    åĪĴ
    -0.06
    éĽ¯
    -0.06
    ä¿ĬæĿ°
    -0.05
    experimental
    -0.05
    POSITIVE LOGITS
    ainte
    0.08
    imuth
    0.08
    aign
    0.07
    æĬ¥ä»ĩ
    0.07
    érica
    0.07
    ailand
    0.07
    à¸Ķูà¸ģ
    0.07
    inkin
    0.07
    lias
    0.07
    orean
    0.07
    Activations Density 0.009%

    No Known Activations