© 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. 44183
    Prev
    Next
    INDEX
    Explanations

    grinding, division, sublimation

    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
    ä¸İæĬķèµĦ
    -0.07
    è°¢ç»Ŀ
    -0.07
    <|box_end|>
    -0.07
    esch
    -0.06
    åħ¬
    -0.06
    pike
    -0.06
     гÑĥм
    -0.06
    è¿ĻæĹłçĸij
    -0.06
    ocs
    -0.06
     |âĢ¢
    -0.06
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.11
     aka
    0.11
    åį³
    0.09
     yani
    0.09
    çĥ¨
    0.08
    ader
    0.08
     cioè
    0.08
    aders
    0.08
     czyli
    0.08
    /u
    0.07
    Activations Density 0.317%

    No Known Activations