© 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. 31972
    Prev
    Next
    INDEX
    Explanations

    asymptotic normality and limit theorems

    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
    feed
    -0.08
     Bow
    -0.07
     ש׼
    -0.07
     feed
    -0.06
     Feed
    -0.06
    éļħ
    -0.06
     SMART
    -0.06
    новÑĮ
    -0.06
    ä¿Ĺè¯Ŀ说
    -0.06
    ä»İæĪij
    -0.06
    POSITIVE LOGITS
    icules
    0.09
    upas
    0.08
     independence
    0.08
    åIJİåı°åĽŀå¤į
    0.07
    udson
    0.07
    eberg
    0.07
    .kr
    0.07
    çĻ¾èĬ±
    0.07
    igas
    0.07
    htub
    0.07
    Activations Density 0.013%

    No Known Activations