© 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. 12433
    Prev
    Next
    INDEX
    Explanations

    mathematical/code symbols and variables

    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
    jep
    -0.08
    สะสม
    -0.06
    åľ¨è¯»
    -0.06
    omin
    -0.06
    imt
    -0.06
    累积
    -0.06
    elib
    -0.06
    ç½
    -0.06
    restart
    -0.06
    æ¼ĵ
    -0.06
    POSITIVE LOGITS
    ãģĭãģijãģ¦
    0.07
    amed
    0.07
    .writ
    0.07
    /export
    0.07
    ivi
    0.07
    è¨Ģ
    0.07
    æĺ¥é£İ
    0.07
    úp
    0.06
    .Factory
    0.06
    éĦĻ
    0.06
    Activations Density 0.004%

    No Known Activations