© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43765
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     Existing
    -0.07
    æºľ
    -0.07
    iad
    -0.07
    etros
    -0.07
    stro
    -0.07
    /original
    -0.07
    èĢģåŁİ
    -0.06
    åѦæĬ¥
    -0.06
    yar
    -0.06
    AMI
    -0.06
    POSITIVE LOGITS
    argout
    0.08
    uret
    0.08
    å¿ĥçļĦ
    0.07
     kte
    0.07
    ouncer
    0.06
    rup
    0.06
    æĪĸå°ı
    0.06
    rados
    0.06
    .Scope
    0.06
    çļĦè§Ħå®ļ
    0.06
    Activations Density 0.006%

    No Known Activations