© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111635
    Prev
    Next
    INDEX
    Explanations

    dance instruction, partners, moves, training, music, away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ly
    -0.12
    ted
    -0.11
     Seas
    -0.10
    ries
    -0.09
    te
    -0.09
    da
    -0.09
    ty
    -0.09
    dle
    -0.09
    ten
    -0.09
    ness
    -0.09
    POSITIVE LOGITS
    floor
    0.18
    able
    0.16
    hall
    0.16
    -offs
    0.13
    board
    0.12
    ster
    0.12
     floor
    0.12
    ability
    0.12
    flo
    0.12
    pad
    0.12
    Activations Density 0.014%

    No Known Activations