© 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. 58904
    Prev
    Next
    INDEX
    Explanations

    code file definitions

    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
    aper
    -0.07
    actus
    -0.07
    '
    -0.06
     commod
    -0.06
    è§Ĩéķľ
    -0.06
     dawn
    -0.06
     author
    -0.06
     cons
    -0.06
    uffs
    -0.06
    åĿIJèIJ½äºİ
    -0.06
    POSITIVE LOGITS
     encount
    0.09
    menin
    0.08
    åŁºæľ¬æ¦Ĥ念
    0.08
    boli
    0.08
    kenal
    0.08
    unku
    0.07
    Ñīем
    0.07
    iedere
    0.07
    volv
    0.07
     Giud
    0.07
    Activations Density 0.543%

    No Known Activations