© 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. 88316
    Prev
    Next
    INDEX
    Explanations

    hit a baseball

    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
     grabbing
    -0.11
     endwhile
    -0.11
     reclaimed
    -0.11
     draining
    -0.11
     enf
    -0.11
     straw
    -0.11
     Hose
    -0.11
     interchangeable
    -0.11
    Dragging
    -0.11
     fren
    -0.11
    POSITIVE LOGITS
     bat
    0.14
     batting
    0.13
     bats
    0.13
     batter
    0.13
     hitter
    0.13
     hit
    0.13
     hits
    0.13
     hitters
    0.12
     Hit
    0.12
     strike
    0.11
    Activations Density 0.181%

    No Known Activations