© 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. 29645
    Prev
    Next
    INDEX
    Explanations

    used with limitations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     spont
    -0.11
     spontaneously
    -0.10
     Tec
    -0.10
     spontaneous
    -0.10
     manifestation
    -0.09
     lottery
    -0.09
     experiencing
    -0.09
     Coach
    -0.09
     casual
    -0.09
     survival
    -0.09
    POSITIVE LOGITS
     influential
    0.21
     publications
    0.17
     controversy
    0.17
     publishing
    0.17
     Influ
    0.15
     publication
    0.15
     scientists
    0.15
     publishes
    0.15
     publish
    0.14
     scientific
    0.14
    Activations Density 0.995%

    No Known Activations