© 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. 51084
    Prev
    Next
    INDEX
    Explanations

    dynamics, conversion, rotation, 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
    æł¼å°Ķ
    -0.07
     prepared
    -0.07
    çݺ
    -0.07
    grid
    -0.07
     Sang
    -0.06
    _Utils
    -0.06
    å¤ļ头
    -0.06
     magn
    -0.06
    è¦ģ说
    -0.06
     princip
    -0.06
    POSITIVE LOGITS
     turnovers
    0.09
    å¾Īå¿«çļĦ
    0.08
     freely
    0.08
    éĢŁçİĩ
    0.08
     rotational
    0.08
    ifetime
    0.08
    éĢŁåº¦å¿«
    0.08
    uth
    0.08
     rotation
    0.08
    å¿«åĪ°
    0.08
    Activations Density 0.032%

    No Known Activations