© 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. 7668
    Prev
    Next
    INDEX
    Explanations

    questions asking for opinions or computations

    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
    æ¯Ķå¦Ĥåľ¨
    -0.08
    åħ°çī¹
    -0.08
    å®ĥ们
    -0.08
    ä½Ĩå®ĥ们
    -0.07
    æľ¬éĻ¢äºİ
    -0.07
    ĩ´
    -0.07
    å°ijå¹´åĦ¿ç«¥
    -0.07
    çī¹åĪ«æĺ¯åľ¨
    -0.07
    ÙĪÙĬÙĦ
    -0.07
     напÑĢимеÑĢ
    -0.07
    POSITIVE LOGITS
    对è¿Ļ个
    0.09
    å°Ĩ该
    0.08
    对该
    0.08
    对è¿Ļ
    0.08
    为该
    0.08
    æѤæŶçļĦ
    0.07
    âĺħâĺħ
    0.07
    è¿Ļ个æķħäºĭ
    0.07
    è¿Ļç§įè¡Į为
    0.07
    å°ĨæѤ
    0.07
    Activations Density 0.478%

    No Known Activations