© 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. 59102
    Prev
    Next
    INDEX
    Explanations

    sigma notation

    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
    perhaps
    -0.09
     perhaps
    -0.08
     talvez
    -0.08
    æľ¬ç½ij
    -0.08
    ä¸İæĬķèµĦ
    -0.07
    以åħįéĢłæĪIJ
    -0.07
    å®īåĪ©
    -0.07
     vielleicht
    -0.07
    aum
    -0.07
     somehow
    -0.07
    POSITIVE LOGITS
    æīĢ以说
    0.09
    æķħéĢī
    0.08
     famously
    0.08
     appunto
    0.08
    çļĦç¡®æĺ¯
    0.08
    æŃ£æĺ¯
    0.07
     extensive
    0.07
    æķħæѤ
    0.07
    èijĹåIJįçļĦ
    0.07
     hence
    0.07
    Activations Density 0.017%

    No Known Activations