© 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. 45425
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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
     warp
    -0.07
     rzÄħd
    -0.07
    ç¦
    -0.07
     warped
    -0.07
    ctors
    -0.07
    çı
    -0.07
     transformations
    -0.07
    è¾¹è§Ĵ
    -0.07
     Gis
    -0.07
    å¦Ĥæ½®
    -0.07
    POSITIVE LOGITS
    ç©¿åĪº
    0.11
     needle
    0.10
    ewire
    0.09
     procedure
    0.09
    éĴĪ
    0.09
    æıĴ
    0.09
     piercing
    0.09
     thÄĥm
    0.08
    æıĴåħ¥
    0.08
     insertion
    0.08
    Activations Density 0.241%

    No Known Activations