© 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. 48126
    Prev
    Next
    INDEX
    Explanations

    electrical conduction or signal transmission

    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
    åĮ¯
    -0.07
    ream
    -0.07
    andu
    -0.06
    hev
    -0.06
    rina
    -0.06
    .hand
    -0.06
    äºĪ
    -0.06
    -handed
    -0.06
    æĬĸ
    -0.06
     Bons
    -0.06
    POSITIVE LOGITS
    åľ¨è¿Ļæĸ¹éĿ¢
    0.16
    è¿Ļæĸ¹éĿ¢çļĦ
    0.11
    è¿Ļæĸ¹éĿ¢
    0.10
    为æѤ
    0.10
    对æѤ
    0.10
    è¿ĻçĤ¹
    0.10
    è¿Ļä¸ĢçĤ¹
    0.09
    åľ¨è¿Ļä¸Ģ
    0.08
    æĻļéĹ´
    0.08
    azer
    0.08
    Activations Density 0.146%

    No Known Activations