© 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. 87602
    Prev
    Next
    INDEX
    Explanations

    Corp, Quebec, Will, Report, Priced, Score

    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
     Sok
    -0.12
     sok
    -0.12
    implements
    -0.11
    antis
    -0.11
     Bren
    -0.11
     forcibly
    -0.10
     propag
    -0.10
     uniquely
    -0.10
    mins
    -0.10
    ago
    -0.09
    POSITIVE LOGITS
     Benef
    0.08
     Temporary
    0.08
     Zimmerman
    0.08
     prem
    0.08
    ACES
    0.08
    ifu
    0.08
     Stephens
    0.08
    /Common
    0.08
     Gros
    0.08
     ann
    0.08
    Activations Density 0.001%

    No Known Activations