© 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. 16629
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

    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
    wards
    -0.09
     commons
    -0.09
     dem
    -0.09
     mines
    -0.08
     diss
    -0.08
     Pont
    -0.08
    adays
    -0.08
     pudd
    -0.08
    /sites
    -0.08
    éĿ
    -0.08
    POSITIVE LOGITS
    fram
    0.11
    endor
    0.10
    orris
    0.10
     Redistributions
    0.10
    inth
    0.09
    itag
    0.09
    iationException
    0.09
    anse
    0.09
     Imper
    0.09
     durable
    0.09
    Activations Density 0.218%

    No Known Activations