© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90579
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     Opportunity
    -0.08
     prov
    -0.08
     migration
    -0.08
     Schn
    -0.08
     Valle
    -0.08
    waters
    -0.08
     crowds
    -0.08
    engu
    -0.08
     Belg
    -0.08
     sco
    -0.08
    POSITIVE LOGITS
    /cop
    0.10
    Ham
    0.10
     pione
    0.09
     Patriot
    0.09
     Raider
    0.09
     trilogy
    0.09
     Dom
    0.09
    /GL
    0.09
     Cool
    0.09
     risen
    0.09
    Activations Density 0.005%

    No Known Activations