© 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. 20056
    Prev
    Next
    INDEX
    Explanations

    printer-friendly

    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
    æľī责任å¿ĥ
    -0.07
    åıĤåĬłå·¥ä½ľ
    -0.07
    ,output
    -0.07
    èĢĮèµ·
    -0.06
     mast
    -0.06
    ลา
    -0.06
    =end
    -0.06
    alani
    -0.06
    bff
    -0.06
     steward
    -0.06
    POSITIVE LOGITS
    опо
    0.08
    ekar
    0.08
    åĽŀéģ¿
    0.07
    对称
    0.07
     symmetric
    0.07
    ardy
    0.07
    éģ¿å¼Ģ
    0.07
    Sym
    0.07
    ä¼´éļı
    0.07
    éģ¿è®©
    0.07
    Activations Density 0.001%

    No Known Activations