© 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. 30739
    Prev
    Next
    INDEX
    Explanations

    win, loss, draws

    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
    atre
    -0.12
    imbus
    -0.11
    /forum
    -0.11
     Orn
    -0.11
    Proto
    -0.11
    hawk
    -0.10
    713
    -0.10
    brick
    -0.10
    lint
    -0.10
    onders
    -0.10
    POSITIVE LOGITS
     factor
    0.11
     catalyst
    0.09
     reel
    0.09
    aine
    0.09
    icial
    0.09
    ingly
    0.08
    -factor
    0.08
     Factor
    0.08
    /dis
    0.08
     stimuli
    0.08
    Activations Density 0.002%

    No Known Activations