© 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. 112497
    Prev
    Next
    INDEX
    Explanations

    highest/best performances or rankings

    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
     UPDATED
    -0.10
     tall
    -0.09
     editorial
    -0.09
     Updates
    -0.08
     styl
    -0.08
     condensed
    -0.08
     tally
    -0.08
     Editorial
    -0.08
     Hollywood
    -0.08
     updates
    -0.08
    POSITIVE LOGITS
    iola
    0.12
    ftar
    0.11
    .FC
    0.10
    ighted
    0.10
     sod
    0.10
     patrons
    0.09
     Manufacturing
    0.09
    (Max
    0.09
    berapa
    0.09
    ks
    0.09
    Activations Density 0.038%

    No Known Activations