© 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. 5084
    Prev
    Next
    INDEX
    Explanations

    score or scores

    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
    eki
    -0.09
     Stout
    -0.09
    rious
    -0.08
    ós
    -0.08
     spark
    -0.08
    riv
    -0.08
    sie
    -0.08
     Receipt
    -0.08
    enen
    -0.08
    spark
    -0.08
    POSITIVE LOGITS
     score
    0.31
     scores
    0.29
     scored
    0.29
     scoring
    0.28
     Score
    0.28
     Scores
    0.28
    score
    0.27
    Score
    0.26
    scores
    0.25
    Scores
    0.24
    Activations Density 0.061%

    No Known Activations