© 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. 50409
    Prev
    Next
    INDEX
    Explanations

    dick, lung, omat, embry, ynthesis

    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
    aby
    -0.10
     fid
    -0.08
    warts
    -0.08
     hairs
    -0.08
    iid
    -0.07
    Paid
    -0.07
     Driver
    -0.07
     spaghetti
    -0.07
    isco
    -0.07
     Paid
    -0.07
    POSITIVE LOGITS
     aggressively
    0.11
     relentlessly
    0.11
     Hancock
    0.11
    /ph
    0.11
     flute
    0.10
     purely
    0.10
     Rahman
    0.10
    .Hand
    0.10
     unilateral
    0.10
     phantom
    0.10
    Activations Density 0.010%

    No Known Activations