© 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. 7785
    Prev
    Next
    INDEX
    Explanations

    surface roughness and texture

    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
    bote
    -0.10
    æŁ¬
    -0.08
     Äijuá»iji
    -0.07
    éĵ¡
    -0.07
    解æķij
    -0.07
     weakening
    -0.07
     hoops
    -0.07
    ç©¿è¶Ĭ
    -0.07
    ql
    -0.07
    è¿ĩåįĬ
    -0.07
    POSITIVE LOGITS
    ç²Ĺç³Ļ
    0.16
    表éĿ¢
    0.13
     surfaces
    0.13
    表éĿ¢çļĦ
    0.12
     surface
    0.12
     повеÑĢÑħноÑģÑĤи
    0.12
    çļĦ表éĿ¢
    0.12
     повеÑĢÑħноÑģÑĤÑĮ
    0.12
    ä¸įå¹³
    0.12
    Surface
    0.11
    Activations Density 0.074%

    No Known Activations