© 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. 61595
    Prev
    Next
    INDEX
    Explanations

    filler words and interjections

    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
    édi
    -0.07
    Disposition
    -0.07
    ìłĢìŀijê¶ĮìŀIJ
    -0.07
    ulina
    -0.07
    à¦ĵয়
    -0.06
    æ²Ļ
    -0.06
    æĺ¯éĿŀ
    -0.06
    tdown
    -0.06
    amor
    -0.06
    égor
    -0.06
    POSITIVE LOGITS
    éģĵéģĵ
    0.08
    clar
    0.07
    /arch
    0.07
    åij±åij±
    0.07
    /course
    0.07
    åĵī
    0.06
    è¹´
    0.06
    arcy
    0.06
    PFN
    0.06
    IFS
    0.06
    Activations Density 0.003%

    No Known Activations