© 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. 35074
    Prev
    Next
    INDEX
    Explanations

    probability sequences of letters

    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
    èĩªå·±
    -0.07
    éĩıåĬĽ
    -0.06
    atil
    -0.06
    缮ä¸Ń
    -0.06
    ä¸ĢåĽŀäºĭ
    -0.06
     Spiegel
    -0.06
     .
    -0.06
    ulton
    -0.06
    åĸľæĢĴ
    -0.06
    åıĪä½ķ
    -0.06
    POSITIVE LOGITS
    ạp
    0.08
    sert
    0.08
    åĮĸåIJĪ
    0.07
    Ñģок
    0.07
    ook
    0.07
    ä¼ģä¸ļ认è¯ģ
    0.07
    Ïĥει
    0.07
    voc
    0.07
    Ñĩего
    0.07
     pronounced
    0.07
    Activations Density 0.033%

    No Known Activations