© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64240
    Prev
    Next
    INDEX
    Explanations

    //, :, is, used, term

    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
    legate
    -0.09
    rox
    -0.08
    iero
    -0.08
    ymbol
    -0.08
    åļı
    -0.08
    idd
    -0.08
    ä¸İæľ¬ç«Ļ
    -0.07
    fra
    -0.07
    plet
    -0.07
    iro
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.07
    å¾·éŁ³
    0.07
    æľīåĵªäºĽåij¢
    0.07
    à¹Ĥà¸Ĭ
    0.07
    åĽł
    0.07
    æĺ¯ä»Ģä¹Īåij¢
    0.06
    åĽłäºº
    0.06
    alina
    0.06
    ãĢįï¼Ī
    0.06
     since
    0.06
    Activations Density 0.007%

    No Known Activations