© 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. 114727
    Prev
    Next
    INDEX
    Explanations

    one by one

    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
     halfway
    -0.10
     midterm
    -0.10
     midway
    -0.09
    wat
    -0.09
    qh
    -0.09
     rowspan
    -0.09
    anno
    -0.09
     Minute
    -0.08
    iswa
    -0.08
     Vanderbilt
    -0.08
    POSITIVE LOGITS
     sequentially
    0.50
     individually
    0.45
     successive
    0.36
     sequential
    0.35
     consec
    0.35
     succession
    0.30
     Sequential
    0.29
     separately
    0.29
     consecutive
    0.27
     progressively
    0.27
    Activations Density 0.781%

    No Known Activations