© 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. 16145
    Prev
    Next
    INDEX
    Explanations

    bowling and bowls

    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
     sting
    -0.11
    coffee
    -0.10
     cattle
    -0.10
     helicopter
    -0.10
     Adobe
    -0.09
    .jasper
    -0.09
     Ej
    -0.09
     pu
    -0.09
     helicopters
    -0.09
     coffee
    -0.09
    POSITIVE LOGITS
     bowling
    0.43
     Bowling
    0.36
     Bowl
    0.25
     bowl
    0.24
     bowls
    0.24
     bow
    0.19
    Bow
    0.18
    bow
    0.17
     Bow
    0.17
     lanes
    0.16
    Activations Density 0.118%

    No Known Activations