© 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. 10582
    Prev
    Next
    INDEX
    Explanations

    current trend or moment

    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
    ç»´æĮģ
    -0.07
    çĭ¡
    -0.07
    egi
    -0.07
     etern
    -0.07
    ulich
    -0.06
    åĪ°çİ°åľº
    -0.06
    缸å¤ĦçļĦ
    -0.06
    è¦ģç»ı常
    -0.06
    ç¶ŃæĮģ
    -0.06
    νομ
    -0.06
    POSITIVE LOGITS
    åħ´èµ·
    0.11
    åħ´
    0.11
    æİĢèµ·äºĨ
    0.11
    æĢĿæ½®
    0.11
    缼è¡Į
    0.11
    è¿ĻèĤ¡
    0.10
    èĪĪ
    0.10
    çĥŃæ½®
    0.10
    äºĨä¸ĢèĤ¡
    0.10
    浪潮
    0.09
    Activations Density 0.451%

    No Known Activations