© 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. 8335
    Prev
    Next
    INDEX
    Explanations

    service in locations

    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
     Icelandic
    -0.10
     Taiwanese
    -0.09
     Danish
    -0.09
     Dutch
    -0.09
     Ashton
    -0.09
     scare
    -0.09
     Schwar
    -0.09
     Irish
    -0.09
     Scottish
    -0.09
     Swedish
    -0.09
    POSITIVE LOGITS
     diversified
    0.11
     advance
    0.11
     USA
    0.11
     every
    0.10
     splitted
    0.10
     Advance
    0.10
    advance
    0.10
    Advance
    0.10
     reputed
    0.10
     pimp
    0.09
    Activations Density 0.062%

    No Known Activations