© 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. 18760
    Prev
    Next
    INDEX
    Explanations

    proclamations; announcements; showings

    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
     perse
    -0.09
     Dur
    -0.09
    anus
    -0.09
    [to
    -0.08
    deaux
    -0.08
     Verm
    -0.08
     retain
    -0.08
     Bere
    -0.08
     Wis
    -0.08
    ç«
    -0.08
    POSITIVE LOGITS
     show
    0.15
     Show
    0.14
     SHOW
    0.12
     demonstrate
    0.12
    show
    0.11
    -confirm
    0.11
    acad
    0.11
     zeigen
    0.10
    Show
    0.10
    OLON
    0.10
    Activations Density 0.001%

    No Known Activations