© 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. 113976
    Prev
    Next
    INDEX
    Explanations

    copyright and licensed licensing

    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
     bev
    -0.10
    cipher
    -0.09
     Milo
    -0.09
    lectic
    -0.09
     revolving
    -0.09
     dun
    -0.09
     Trades
    -0.09
     -,
    -0.09
    rellas
    -0.09
    lectron
    -0.09
    POSITIVE LOGITS
     appropriately
    0.09
     Kaiser
    0.09
    unde
    0.09
    okie
    0.09
     figur
    0.09
    ning
    0.09
     ethic
    0.08
     taxing
    0.08
    ting
    0.08
    tera
    0.08
    Activations Density 0.002%

    No Known Activations