© 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. 4583
    Prev
    Next
    INDEX
    Explanations

    CH and SH sounds

    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
    à§įত
    -0.13
    ation
    -0.11
     ÐŁÐ¾Ñħожие
    -0.09
    ATION
    -0.08
    ehme
    -0.08
    Ñīик
    -0.08
    urier
    -0.08
    ÑģÑĮ
    -0.08
    ãģ¾ãģ¾
    -0.08
    iente
    -0.07
    POSITIVE LOGITS
    indsight
    0.14
    ancock
    0.13
    enticated
    0.12
    elloworld
    0.12
    enticate
    0.12
    neider
    0.12
    reiber
    0.12
    retien
    0.11
    onest
    0.11
    ometown
    0.11
    Activations Density 2.439%

    No Known Activations