© 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. 25861
    Prev
    Next
    INDEX
    Explanations

    correct and acceptable

    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
    çIJ¢
    -0.08
    å©´
    -0.07
    ظÙĬÙģ
    -0.07
     Depends
    -0.07
     desem
    -0.07
    ä¸Ĭé£İ
    -0.07
    æĽ¾ç»ı说è¿ĩ
    -0.06
     mene
    -0.06
    ä¸įå®ļ
    -0.06
    æĥ³ä½ł
    -0.06
    POSITIVE LOGITS
    符åIJĪè¦ģæ±Ĥ
    0.12
    满足
    0.10
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.09
     satisfies
    0.09
    符åIJĪ
    0.09
    满足äºĨ
    0.09
     satisfy
    0.09
    符åIJĪæĿ¡ä»¶
    0.08
    å®Įç¾İ
    0.08
     acceptable
    0.08
    Activations Density 0.015%

    No Known Activations