© 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. 25674
    Prev
    Next
    INDEX
    Explanations

    closing parentheses ) and braces }

    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
    entang
    -0.08
    [--
    -0.08
     ØŃاضر
    -0.08
    _DIGEST
    -0.07
    æĶ¿åºľåħ¬åijĬ
    -0.07
    !I
    -0.07
    èĿł
    -0.07
    argout
    -0.07
    æİĴè¡Įæ¦ľåįķ
    -0.07
    ç»ıèIJ¥é¡¹çĽ®
    -0.07
    POSITIVE LOGITS
    ¬ģ
    0.07
     Lain
    0.06
    ;.
    0.06
     Chor
    0.06
    QUIT
    0.06
    į
    0.06
    éĢŀ
    0.06
    大ä¸įäºĨ
    0.06
    çĶ»
    0.06
    çĥĤ
    0.06
    Activations Density 0.009%

    No Known Activations