© 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. 114056
    Prev
    Next
    INDEX
    Explanations

    Filed: date, dollars: amount, posts: topic

    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
     reprint
    -0.11
     Ingram
    -0.10
    morgan
    -0.10
     challenger
    -0.10
     Booker
    -0.09
    nej
    -0.09
     epis
    -0.09
    antino
    -0.09
     Chains
    -0.09
     Billboard
    -0.09
    POSITIVE LOGITS
    (New
    0.10
     âľĵ
    0.08
     autof
    0.08
     rightfully
    0.08
     mixed
    0.08
    oner
    0.08
    .wik
    0.08
     __(
    0.08
    ä¿®
    0.08
     Barg
    0.08
    Activations Density 0.003%

    No Known Activations