© 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. 37931
    Prev
    Next
    INDEX
    Explanations

    units of physical quantities

    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
    è¦ģæ±ĤåIJĦ
    -0.08
    oces
    -0.08
    icated
    -0.08
    cito
    -0.08
    nements
    -0.08
    untut
    -0.08
    ostro
    -0.08
    à¸ģà¹ĩà¸ķาม
    -0.07
    aranya
    -0.07
     consecutive
    -0.07
    POSITIVE LOGITS
    imension
    0.06
     times
    0.06
    羣å®ŀ
    0.06
    ãĤĪãģĨãģ§
    0.06
    è¿ĩä¸įåİ»
    0.06
    è´¨éĩıçļĦ
    0.06
    вин
    0.05
    çĸ¯äºĨ
    0.05
    çļĦä¸Ģç±»
    0.05
    æī±ãģĦ
    0.05
    Activations Density 0.003%

    No Known Activations