© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7712
    Prev
    Next
    INDEX
    Explanations

    train, trained, trains

    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
    arel
    -0.11
    omes
    -0.11
    fort
    -0.11
     plight
    -0.11
     prone
    -0.11
    creen
    -0.11
    allen
    -0.11
    usu
    -0.11
    TC
    -0.11
    tracted
    -0.11
    POSITIVE LOGITS
     replacements
    0.11
     muscles
    0.10
     bilingual
    0.09
     unr
    0.09
     extensively
    0.09
     haz
    0.09
     replacement
    0.09
     minds
    0.08
    /train
    0.08
     trainable
    0.08
    Activations Density 0.054%

    No Known Activations