© 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. 18405
    Prev
    Next
    INDEX
    Explanations

    specifically, namely

    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
    æĹłå¤Ħä¸įåľ¨
    -0.08
    ivel
    -0.07
    éģĤ
    -0.07
    emas
    -0.07
    havn
    -0.07
    utnik
    -0.07
    lex
    -0.07
    brem
    -0.07
    eras
    -0.06
    æĽľ
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.08
    æ¯Ķå¦Ĥ
    0.08
    è¿Ļåľ¨
    0.07
    icularly
    0.07
    _-
    0.07
    å¦Ĥçģ«
    0.07
    è¿Ļæĺ¯
    0.07
     Specifically
    0.07
     namely
    0.07
    ullet
    0.07
    Activations Density 0.076%

    No Known Activations