© 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. 63577
    Prev
    Next
    INDEX
    Explanations

    replacements or airplane

    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¸įæĺ¯å¾Ī
    -0.07
    pst
    -0.07
    lico
    -0.07
    utsch
    -0.07
    缴æİ¥ä»İ
    -0.07
    鼶åħ«
    -0.07
    çĶľçļĦ
    -0.07
    érés
    -0.07
    æŃ»æ´»
    -0.07
    æĬĢæľ¯æĶ¹éĢł
    -0.07
    POSITIVE LOGITS
    æīįè¡Į
    0.08
    æĺ¯åĶ¯ä¸Ģ
    0.08
    æľī两ç§į
    0.07
    æĪĸèĢħ
    0.07
    符åIJĪè¦ģæ±Ĥ
    0.06
    meister
    0.06
     appunto
    0.06
    èģª
    0.06
    æīįèĥ½ä¿Ŀè¯ģ
    0.06
    åĮ»åѦä¼ļ
    0.06
    Activations Density 0.011%

    No Known Activations