© 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. 30934
    Prev
    Next
    INDEX
    Explanations

    numbers and time units

    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
    æĢ»æĶ¶åħ¥
    -0.07
    æĢ»éĩı
    -0.07
    æĢ»éĿ¢ç§¯
    -0.07
    ëı¼
    -0.07
     Bronx
    -0.06
    IMIZE
    -0.06
     lel
    -0.06
    _tot
    -0.06
    ä¿ĿæĬ¤æ³ķ
    -0.06
     getTotal
    -0.06
    POSITIVE LOGITS
    è´¼
    0.07
     footh
    0.07
    ÑĢеменно
    0.07
    éģĩè§ģä½ł
    0.07
    åij¼
    0.07
    quot
    0.07
    าศ
    0.07
    æ¼ĵ
    0.06
    èĪĴ
    0.06
    enson
    0.06
    Activations Density 0.008%

    No Known Activations