© 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. 44601
    Prev
    Next
    INDEX
    Explanations

    tic-tac-toe

    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
    .utf
    -0.08
    kowski
    -0.07
    borne
    -0.07
     Libri
    -0.07
    erts
    -0.07
    çŃīå¤Ħ
    -0.06
    lande
    -0.06
     sottos
    -0.06
    à¤Ĺत
    -0.06
    tle
    -0.06
    POSITIVE LOGITS
    æķ°åŃĹ
    0.09
    æį¢
    0.08
    ngr
    0.08
    çļĦä¸įåIJĮ
    0.08
    æĽ¿ä»£
    0.07
    ä¸įåIJĮçļĦ
    0.07
    meld
    0.07
    gant
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
    æĽ¿æį¢
    0.07
    Activations Density 0.013%

    No Known Activations