© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4155
    Prev
    Next
    INDEX
    Explanations

    motion

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    éĢĴ
    -0.23
    .Comparator
    -0.23
    ppard
    -0.20
    --;↵↵
    -0.20
    饱åĴĮ
    -0.19
     ?>↵↵↵
    -0.19
    _dept
    -0.19
    apro
    -0.19
     saturation
    -0.18
    ç¼Ľ
    -0.18
    POSITIVE LOGITS
     movement
    0.47
     movements
    0.44
     motion
    0.40
     motions
    0.38
    è¿IJåĬ¨
    0.36
     Movement
    0.36
    movement
    0.34
     движениÑı
    0.31
    Movement
    0.31
    motion
    0.31
    Activations Density 0.896%

    No Known Activations