© 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. 18766
    Prev
    Next
    INDEX
    Explanations

    okay, ok, maybe, perhaps, admittedly

    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
    itta
    -0.12
    [((
    -0.11
    ohl
    -0.11
     oh
    -0.11
    atus
    -0.10
    rene
    -0.10
     Walsh
    -0.10
    Pager
    -0.10
     Maker
    -0.09
    anz
    -0.09
    POSITIVE LOGITS
     maybe
    0.22
    maybe
    0.18
     perhaps
    0.16
    Maybe
    0.16
     Maybe
    0.16
    aybe
    0.12
     admittedly
    0.12
     MAY
    0.12
     sometimes
    0.12
     Perhaps
    0.12
    Activations Density 0.023%

    No Known Activations