© 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. 55649
    Prev
    Next
    INDEX
    Explanations

    special characters and programming constructs

    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
    çĶ¨çĶµ
    -0.07
    tt
    -0.06
    table
    -0.06
    åIJĥä¸ľè¥¿
    -0.06
    ä¸įå°ij人
    -0.06
    Ĥ¬
    -0.06
    baum
    -0.06
    dd
    -0.06
    tf
    -0.06
    ç§įç§į
    -0.05
    POSITIVE LOGITS
     **:**
    0.09
     fili
    0.08
    éģĵå·¥åºı
    0.08
    asiun
    0.08
    berman
    0.08
    isphere
    0.08
    ÑĢовÑģкий
    0.08
    PRS
    0.07
     MANAG
    0.07
    otos
    0.07
    Activations Density 0.002%

    No Known Activations