© 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. 48223
    Prev
    Next
    INDEX
    Explanations

    Sept/September names and dates

    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
    urer
    -0.09
     Kale
    -0.08
    nell
    -0.08
     spotting
    -0.08
    brig
    -0.08
     Powered
    -0.08
    soc
    -0.07
    urers
    -0.07
    uits
    -0.07
     Kir
    -0.07
    POSITIVE LOGITS
     Sep
    0.14
     Sept
    0.14
     sep
    0.13
    ultur
    0.12
    ember
    0.12
    /oct
    0.11
    Sept
    0.11
    Sep
    0.11
    MBER
    0.11
    -Nov
    0.11
    Activations Density 0.037%

    No Known Activations