© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47065
    Prev
    Next
    INDEX
    Explanations

    queries, samples, stream, observation

    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
    è¢
    -0.09
    coa
    -0.08
     overst
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.08
    ä¿Ŀ驾
    -0.07
    unner
    -0.07
    wic
    -0.07
    èĢĮæĺ¯åĽłä¸º
    -0.07
    ç¼ĶéĢł
    -0.07
    å¤ĩ
    -0.07
    POSITIVE LOGITS
    èİ·åıĸ
    0.08
    æĿ¥èİ·åıĸ
    0.08
     oracle
    0.08
     informative
    0.07
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    æıIJä¾Ľä»»ä½ķ
    0.07
    询éĹ®
    0.07
    交æµģ
    0.07
    æĥ³çŁ¥éģĵ
    0.07
    æĶ¾é¡Į
    0.07
    Activations Density 0.024%

    No Known Activations