© 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. 3877
    Prev
    Next
    INDEX
    Explanations

    bug report issues or fixing

    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
    QueryBuilder
    -0.06
    ç»´å°Ķ
    -0.06
    çĻ½æĿ¡
    -0.06
    ç´¯
    -0.06
    èµĦæł¼æĿ¡ä»¶
    -0.06
    YNC
    -0.06
     consec
    -0.06
    çī¹å°Ķ
    -0.06
    亲亲
    -0.06
    itkan
    -0.06
    POSITIVE LOGITS
    èĬĻèĵī
    0.08
     Afr
    0.08
    atron
    0.07
    å±¥è¡Į
    0.07
    _helpers
    0.07
    .setTimeout
    0.07
     Verst
    0.07
    çĩİ
    0.07
    verst
    0.07
    enario
    0.07
    Activations Density 0.001%

    No Known Activations