© 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. 8230
    Prev
    Next
    INDEX
    Explanations

    License document clauses

    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
    262
    -0.08
     Hermes
    -0.08
     explicit
    -0.08
     wrapped
    -0.08
    sd
    -0.07
     unfavorable
    -0.07
     mutually
    -0.07
    ehr
    -0.07
     localhost
    -0.07
     coincide
    -0.07
    POSITIVE LOGITS
    inth
    0.11
     Kara
    0.11
    ocker
    0.11
    onth
    0.10
    olie
    0.10
    (`↵
    0.10
    weg
    0.10
    453
    0.10
    ither
    0.10
    omp
    0.10
    Activations Density 0.005%

    No Known Activations