© 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. 13179
    Prev
    Next
    INDEX
    Explanations

    energy units and rates

    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¦ĨçĽĸçİĩ
    -0.07
    欧äºļ
    -0.07
    带宽
    -0.07
    åĬªåĬĽæıIJé«ĺ
    -0.07
     respiro
    -0.07
    -width
    -0.07
    åĽĽä¸ªèĩªä¿¡
    -0.06
    èı©æıIJ
    -0.06
    çľ¼åľĪ
    -0.06
    éĹ´è·Ŀ
    -0.06
    POSITIVE LOGITS
    çļĦèĥ½éĩı
    0.12
     energy
    0.12
    èĥ½éĩı
    0.11
    èĥ½éĩıçļĦ
    0.10
     ÑįнеÑĢгии
    0.10
     expended
    0.10
    energy
    0.10
     jou
    0.10
     energia
    0.09
     Jou
    0.09
    Activations Density 0.005%

    No Known Activations