© 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. 90983
    Prev
    Next
    INDEX
    Explanations

    numbers after date

    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
     COVID
    -0.23
    COVID
    -0.21
     coronavirus
    -0.21
     Coronavirus
    -0.21
     Trump
    -0.19
     Brexit
    -0.18
    -Trump
    -0.18
     covid
    -0.18
     ðŁij
    -0.17
     Covid
    -0.17
    POSITIVE LOGITS
     war
    0.10
     terrific
    0.09
     Met
    0.09
     Bard
    0.08
     pimp
    0.08
     equipments
    0.08
     iPod
    0.08
     inflation
    0.08
     Wagner
    0.08
     liber
    0.08
    Activations Density 0.295%

    No Known Activations