© 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. 28637
    Prev
    Next
    INDEX
    Explanations

    email to, Original Washington, drops of, vim:, agent genipin, .email to, Original Washington, drops of, vim:, agent genipin,

    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
    ema
    -0.10
    nc
    -0.09
     pow
    -0.09
     items
    -0.09
     inventory
    -0.08
    ós
    -0.08
     leth
    -0.08
    chs
    -0.08
     boo
    -0.08
    emic
    -0.08
    POSITIVE LOGITS
     Brooks
    0.10
     RD
    0.10
    FINE
    0.09
     Weston
    0.09
    poi
    0.09
     LB
    0.09
    Monkey
    0.09
    DN
    0.09
     testimon
    0.09
     eman
    0.09
    Activations Density 0.001%

    No Known Activations