© 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. 62516
    Prev
    Next
    INDEX
    Explanations

    torque and power output

    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
    æĥĬéŃĤ
    -0.08
    严éĩįè¿Ŀæ³ķ
    -0.07
    çĮĸ
    -0.07
     nested
    -0.06
    éĿ¢åĢĴ
    -0.06
    伶
    -0.06
    åµĮå¥Ĺ
    -0.06
    æļ´éľ²
    -0.06
    spy
    -0.06
    ìa
    -0.06
    POSITIVE LOGITS
    åĩºåĬĽ
    0.12
    è¾ĵåĩºåĬŁçİĩ
    0.11
    è¾ĵåĩº
    0.11
     output
    0.11
     capability
    0.10
    /power
    0.10
    è¾ĵåĩºçļĦ
    0.10
    輸åĩº
    0.10
     ë°ľíľĺ
    0.10
     Ñģилой
    0.10
    Activations Density 0.043%

    No Known Activations