© 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. 117600
    Prev
    Next
    INDEX
    Explanations

    date formats like 01/04, 06/01

    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
     slack
    -0.09
     sparing
    -0.08
     resh
    -0.08
     Spar
    -0.08
    PAD
    -0.08
     Shadow
    -0.08
     spare
    -0.07
     lat
    -0.07
     priv
    -0.07
     Comment
    -0.07
    POSITIVE LOGITS
    Verified
    0.13
    ERV
    0.11
     Jefferson
    0.11
    ,id
    0.11
     ISBN
    0.10
    thon
    0.10
     upholstery
    0.10
     priced
    0.10
     satisfied
    0.10
     Crosby
    0.10
    Activations Density 0.001%

    No Known Activations