© 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. 31724
    Prev
    Next
    INDEX
    Explanations

    ciliary muscle

    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
     proceder
    -0.08
    yim
    -0.08
     breit
    -0.08
    _DEFINE
    -0.08
    èµĶ
    -0.08
    çļ®çĤİ
    -0.07
    installer
    -0.07
    cies
    -0.07
     procedere
    -0.07
    flows
    -0.07
    POSITIVE LOGITS
    è°ĥèĬĤ
    0.09
     accommodation
    0.08
     reflex
    0.07
    調ç¯Ģ
    0.07
    aptive
    0.07
     Accom
    0.07
    accom
    0.06
     accommod
    0.06
     capacity
    0.06
     effort
    0.06
    Activations Density 0.005%

    No Known Activations