© 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. 22637
    Prev
    Next
    INDEX
    Explanations

    MATRIX

    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
    cg
    -0.06
     Gug
    -0.06
    庶
    -0.06
    _FMT
    -0.06
    è¢ħ
    -0.06
    èijĨ
    -0.06
    ä¸įåIJ¬
    -0.06
    éģĵ人
    -0.06
    åįĹåŁİ
    -0.06
    æĿ¥åĽŀ
    -0.06
    POSITIVE LOGITS
    ÃŃmica
    0.08
    iede
    0.08
    åħĭéļ¾
    0.07
     getr
    0.07
    ÛĮاÙĨ
    0.07
    è½Ł
    0.07
    obl
    0.07
    æŃ¤èµ·å½¼
    0.07
    MATRIX
    0.07
    antry
    0.07
    Activations Density 0.092%

    No Known Activations