© 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. 22601
    Prev
    Next
    INDEX
    Explanations

    questions starting with "is" or "how"

    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
    Å¡ÃŃ
    -0.07
     sÃłng
    -0.07
    _LR
    -0.06
    ldr
    -0.06
    Æ°Æ¡ng
    -0.06
    urement
    -0.06
    åħĭåĪ©
    -0.06
    antin
    -0.06
    ĸ
    -0.06
    llib
    -0.06
    POSITIVE LOGITS
    ç¾ļ
    0.09
    rund
    0.08
    erald
    0.07
    æĹħé¦Ĩ
    0.07
    åĽłæĿIJ
    0.07
     rued
    0.07
    mouseover
    0.07
    theless
    0.07
     Edels
    0.07
    bay
    0.07
    Activations Density 0.042%

    No Known Activations