© 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. 47934
    Prev
    Next
    INDEX
    Explanations

    Day News

    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
    ÙĤØ·
    -0.07
    å¹´æľĪ
    -0.06
    бÑĢÑĮ
    -0.06
     loops
    -0.06
     Che
    -0.06
    å¥Īä½ķ
    -0.06
    anda
    -0.06
    ç¿ħ
    -0.06
     Idea
    -0.06
    بر
    -0.06
    POSITIVE LOGITS
    kana
    0.08
    ä½¼
    0.07
    istine
    0.07
    æĪij常常
    0.07
    alow
    0.07
    xo
    0.07
    ä¸ĭ载次æķ°
    0.07
    Ñįл
    0.07
    jist
    0.07
    åįıå®ļ
    0.07
    Activations Density 0.020%

    No Known Activations