© 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. 27097
    Prev
    Next
    INDEX
    Explanations

    names ending in -ard, -arn, -aw, -av, -ife, -urn, -iqu

    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
     otherwise
    -0.09
     usual
    -0.08
     Few
    -0.08
     leg
    -0.08
    acha
    -0.08
     whip
    -0.08
     tex
    -0.08
    arks
    -0.08
     Whole
    -0.07
     padded
    -0.07
    POSITIVE LOGITS
    ió
    0.10
     meaningless
    0.10
    ICO
    0.09
    .microsoft
    0.09
     medidas
    0.09
    osoph
    0.09
     methodologies
    0.09
    udget
    0.09
     measurements
    0.09
     Lips
    0.09
    Activations Density 0.231%

    No Known Activations