© 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. 87750
    Prev
    Next
    INDEX
    Explanations

    bulk purchase offers

    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
    fh
    -0.10
     inexpensive
    -0.10
     gratis
    -0.10
     Dashboard
    -0.09
     Mend
    -0.09
     tread
    -0.09
     Cost
    -0.09
     refunds
    -0.09
     payoff
    -0.09
     tame
    -0.09
    POSITIVE LOGITS
     bulk
    0.15
     Bulk
    0.13
     referrals
    0.12
    bulk
    0.12
    Bulk
    0.12
     signing
    0.12
     bund
    0.11
     early
    0.11
     bundled
    0.10
     Bund
    0.10
    Activations Density 0.165%

    No Known Activations