© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33953
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    quoise
    -0.08
     stalk
    -0.08
    645
    -0.08
     strokes
    -0.08
     Appliances
    -0.08
    onaut
    -0.08
     zig
    -0.08
     Spare
    -0.07
    obi
    -0.07
    Forg
    -0.07
    POSITIVE LOGITS
    perf
    0.13
    thrown
    0.11
    zu
    0.11
    hoff
    0.10
     reb
    0.10
     interruption
    0.10
     eminent
    0.09
     Alleg
    0.09
     inne
    0.09
    ham
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.