© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8731
    Prev
    Next
    INDEX
    Explanations

    walking and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     asleep
    -0.10
    озд
    -0.09
     locked
    -0.09
     rend
    -0.09
     sleeps
    -0.09
     hyp
    -0.08
    overn
    -0.08
     locking
    -0.08
    Offsets
    -0.08
     cray
    -0.08
    POSITIVE LOGITS
     walking
    0.25
     walk
    0.22
     walks
    0.21
     Walking
    0.21
    Walking
    0.21
    walking
    0.20
     Walk
    0.20
     walked
    0.19
    _walk
    0.18
    Walk
    0.17
    Activations Density 0.242%

    No Known Activations