© 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. 59851
    Prev
    Next
    INDEX
    Explanations

    (C) Copyright

    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
    âĢ¦),
    -0.09
     Administra
    -0.07
    åıĪåĥı
    -0.07
    evere
    -0.07
    éĨīäºĨ
    -0.07
    æľīæĿĥä¿ĿçķĻ
    -0.07
     Playstation
    -0.07
    —which
    -0.07
    —for
    -0.07
    ä»Ĭ天æĺ¯
    -0.07
    POSITIVE LOGITS
    Ñij
    0.07
    âĢij
    0.07
    alian
    0.06
    ationale
    0.06
    cheme
    0.06
     vs
    0.06
     Rel
    0.06
    âĢIJ
    0.06
    (self
    0.06
    ä¸ĬçŃī
    0.06
    Activations Density 0.008%

    No Known Activations