© 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. 38214
    Prev
    Next
    INDEX
    Explanations

    :) emoticon

    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
    nya
    -0.16
    er
    -0.15
    çļĦ
    -0.13
    mente
    -0.12
    ÛĮ
    -0.12
    ä½Ĩä¸įéĻIJäºİ
    -0.11
    erer
    -0.10
    اÙĭ
    -0.10
    ly
    -0.10
    hent
    -0.10
    POSITIVE LOGITS
    и
    0.09
    sver
    0.09
    zelfde
    0.08
    ਼
    0.08
    s
    0.08
    alog
    0.08
    çļĦéĤ£äºĽ
    0.08
    ä¸ĭæĸ¹äºĮç»´çłģ
    0.08
    .jquery
    0.08
    ãĥ¼
    0.07
    Activations Density 0.001%

    No Known Activations