© 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. 14301
    Prev
    Next
    INDEX
    Explanations

    pinpoint accuracy

    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
    ahi
    -0.10
    .ma
    -0.09
    ikh
    -0.09
     Nielsen
    -0.09
     Magnus
    -0.09
    706
    -0.09
    628
    -0.09
    printStats
    -0.08
    bell
    -0.08
    _hide
    -0.08
    POSITIVE LOGITS
     accuracy
    0.14
    -point
    0.12
     precision
    0.12
    ered
    0.12
     focus
    0.12
     accurate
    0.11
    ed
    0.11
     sized
    0.11
    -focus
    0.11
     accurately
    0.11
    Activations Density 0.004%

    No Known Activations