© 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. 45943
    Prev
    Next
    INDEX
    Explanations

    torque and rotational motion

    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
    amel
    -0.07
    éļĺ
    -0.06
    éĿ¢è²Į
    -0.06
    äºĴèģĶäºĴéĢļ
    -0.06
    çİ°å®ŀ
    -0.06
     Rational
    -0.06
    ä¿¡éģĵ
    -0.06
     Ter
    -0.06
    ĻĤ
    -0.06
    ÙĤاÙĨ
    -0.06
    POSITIVE LOGITS
    æĶ¯çĤ¹
    0.10
    æīŃ磩
    0.09
     torque
    0.08
     Pivot
    0.08
    shaft
    0.08
     pivot
    0.08
    æĹĭ转
    0.08
     clockwise
    0.08
    æľĢ大æīŃ磩
    0.08
     piv
    0.08
    Activations Density 0.002%

    No Known Activations