© 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. 55571
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    åļ¼
    -0.08
    /tags
    -0.08
    æĶ¾ä¸ĭ
    -0.07
    å¸ĮæľĽèĩªå·±
    -0.07
    èĽ
    -0.07
    deploy
    -0.07
    amn
    -0.07
     koll
    -0.06
    æĺ¯åŃ©åŃIJ
    -0.06
    .coll
    -0.06
    POSITIVE LOGITS
    nesc
    0.08
    atts
    0.07
    ijľ
    0.07
    å®ľåħ´
    0.07
    åŃ£åIJİ
    0.07
    ä¼ģä¸ļä¿¡æģ¯
    0.07
    é¾ĻèĪŁ
    0.07
    LLU
    0.07
    è°ħ
    0.07
    atter
    0.06
    Activations Density 0.003%

    No Known Activations