© 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. 16540
    Prev
    Next
    INDEX
    Explanations

    punctuation or special characters

    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
    opyright
    -0.09
    etul
    -0.07
    воÑĢÑı
    -0.07
    oulos
    -0.07
    ipun
    -0.07
    ãģĽãĤĵ
    -0.07
    ç«ĭåį³ä¸ĭè½½
    -0.07
    iasm
    -0.07
    ÑĽÐ¸
    -0.07
    æĪij社
    -0.07
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.09
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    äºĭåįĬåĬŁåĢį
    0.07
    oo
    0.07
    ï¸ı
    0.07
    éĺ¿æĭī伯
    0.07
    ä¸įåı¯æĢĿè®®
    0.06
    身临åħ¶å¢ĥ
    0.06
    ettes
    0.06
    %C
    0.06
    Activations Density 0.153%

    No Known Activations