© 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. 44713
    Prev
    Next
    INDEX
    Explanations

    speleonectes tulumensis

    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
    erty
    -0.08
    ä¸įåŃĺåľ¨
    -0.08
    rew
    -0.08
    éļ¾å¾Ĺ
    -0.07
    ystal
    -0.07
    åºĶ该ä¸įä¼ļ
    -0.07
    æ¡£
    -0.07
    _imag
    -0.07
     invisible
    -0.07
     unseen
    -0.07
    POSITIVE LOGITS
    èĻ½æľī
    0.12
    èĻ½çĦ¶
    0.12
    èĻ½çĦ¶åľ¨
    0.11
    èĻ½çĦ¶æľī
    0.11
    èĻ½
    0.11
    èĻ½æĺ¯
    0.10
    éĽĸçĦ¶
    0.10
     although
    0.10
    èĻ½çĦ¶æĺ¯
    0.10
     zwar
    0.09
    Activations Density 0.019%

    No Known Activations