© 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. 28602
    Prev
    Next
    INDEX
    Explanations

    occupy space or extent

    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
    egn
    -0.08
    kent
    -0.07
    ä»»ä½ķäºĭæĥħ
    -0.07
    亲è¿ij
    -0.07
     yourself
    -0.07
    å¤ĸåĽ½è¯ŃåŃ¦æł¡
    -0.07
    çĽ¸çŁ¥
    -0.07
    urre
    -0.06
    è¿Ļç§įäºĭ
    -0.06
    ä»Ģä¹ĪåİŁåĽł
    -0.06
    POSITIVE LOGITS
    æķ´ä¸ª
    0.11
    åįłæį®
    0.11
     entirety
    0.10
    æķ´åĢĭ
    0.10
     occupy
    0.10
     occupies
    0.09
    大éĥ¨åĪĨ
    0.09
    åįłæį®äºĨ
    0.09
    æĪĸéĥ¨åĪĨ
    0.09
     occupying
    0.09
    Activations Density 0.153%

    No Known Activations