© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4834
    Prev
    Next
    INDEX
    Explanations

    numbers, characters, and words in certain contexts

    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
    Negative Logits
    è°ħ
    -0.07
    åĢ
    -0.07
    æĹłéĿŀ
    -0.06
    aksud
    -0.06
    urator
    -0.06
    fol
    -0.06
    ç¼ĵ
    -0.06
    çļ®ä¹¦
    -0.06
    शà¥Ģ
    -0.06
    ç¼ħ
    -0.06
    POSITIVE LOGITS
    ydd
    0.08
    irin
    0.08
    å°¼æĸ¯
    0.08
    æĶ¹çīĪ
    0.08
    è¿ĻäºĽéĹ®é¢ĺ
    0.07
    usche
    0.07
    ÙĪتÙĬÙĨ
    0.07
    å¾Īæľī趣
    0.07
    èĬ±çµ®
    0.07
    è¿Ļæł·çļĦéĹ®é¢ĺ
    0.07
    Activations Density 0.027%

    No Known Activations