© 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. 6332
    Prev
    Next
    INDEX
    Explanations

    accuracy and inaccuracy

    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
     healthier
    -0.09
     Ton
    -0.09
     ener
    -0.09
     adjoining
    -0.08
     observable
    -0.08
     effortlessly
    -0.08
     spontaneously
    -0.08
    ote
    -0.08
     dying
    -0.08
    uet
    -0.08
    POSITIVE LOGITS
     accurate
    0.34
     inaccurate
    0.33
     accuracy
    0.33
     Accuracy
    0.32
    accur
    0.30
    accuracy
    0.30
    Accuracy
    0.29
     accur
    0.27
     useful
    0.26
     unreliable
    0.25
    Activations Density 0.924%

    No Known Activations