© 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. 62112
    Prev
    Next
    INDEX
    Explanations

    motion, displacement, and rotation

    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
    ellis
    -0.07
    èķ
    -0.07
    çĨı
    -0.07
     Neb
    -0.07
     weaker
    -0.07
     brackets
    -0.07
    æĬļ顺
    -0.07
    êle
    -0.07
     strength
    -0.07
     bracket
    -0.07
    POSITIVE LOGITS
     movements
    0.09
     displ
    0.09
    ä½į移
    0.08
    移åĬ¨
    0.08
     displacement
    0.08
    çļĦ移åĬ¨
    0.08
    íĥĿ
    0.08
     motions
    0.07
     changes
    0.07
     monitored
    0.07
    Activations Density 0.001%

    No Known Activations