© 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. 60034
    Prev
    Next
    INDEX
    Explanations

    urls and documentation links

    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
    æĭīèµ·
    -0.08
    è¿Ļæł·çļĦæĥħåĨµ
    -0.07
    weiler
    -0.07
     Conserv
    -0.06
    æľīè¿Ļæł·
    -0.06
    ä¹Łå°±æĦıåij³çĿĢ
    -0.06
    è§Ħå¾ĭçļĦ
    -0.06
    ipsis
    -0.06
    æĺ¯è¿Ļæł·çļĦ
    -0.06
    ç»ĵæŀľè¡¨æĺİ
    -0.06
    POSITIVE LOGITS
    ocha
    0.09
     Various
    0.08
    以åıĬåIJĦç§į
    0.08
    ä¹ĭçªĹ
    0.08
    åIJĦç§į
    0.07
    але
    0.07
    Various
    0.07
    NullOrEmpty
    0.07
     various
    0.07
    olet
    0.07
    Activations Density 0.043%

    No Known Activations