© 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. 90435
    Prev
    Next
    INDEX
    Explanations

    gold, goldmine, goldcorp, goldman, goldstone, gold's

    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
     coin
    -0.13
     coins
    -0.11
     Coin
    -0.10
    imir
    -0.10
     pier
    -0.10
     gold
    -0.10
     Coins
    -0.10
    anse
    -0.09
    Coin
    -0.09
     zar
    -0.09
    POSITIVE LOGITS
    /OR
    0.10
     Snow
    0.10
     Scor
    0.09
     Porn
    0.09
    Tau
    0.09
    owell
    0.08
     invis
    0.08
     reductions
    0.08
    PECT
    0.08
     Joined
    0.08
    Activations Density 0.011%

    No Known Activations