© 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. 44595
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    æĹ¥æ¶Īæģ¯
    -0.08
    æĢ§ä»¥åıĬ
    -0.08
    以åıĬåIJĦç§į
    -0.07
    å¦ĩ人
    -0.07
    !]
    -0.07
    izzi
    -0.07
    hood
    -0.07
    hluk
    -0.07
    åĿŁ
    -0.07
     Giorg
    -0.07
    POSITIVE LOGITS
    åijĬ
    0.07
    人åĬĽ
    0.07
    ç»´åħĭ
    0.06
    icum
    0.06
    éŁ³
    0.06
    OrFail
    0.06
    icher
    0.06
    aña
    0.06
    交éĢļ
    0.06
    ä½ij
    0.06
    Activations Density 0.044%

    No Known Activations