© 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. 111473
    Prev
    Next
    INDEX
    Explanations

    unusual or rare occurrences

    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
    Negative Logits
    Interpreter
    -0.09
     revelations
    -0.09
     meanwhile
    -0.09
     Conversation
    -0.09
     evid
    -0.09
     Tent
    -0.09
     hints
    -0.08
    uren
    -0.08
     tent
    -0.08
    conversation
    -0.08
    POSITIVE LOGITS
     odd
    0.13
     Cur
    0.13
     unusual
    0.13
     usually
    0.13
     rarely
    0.12
     curiosity
    0.12
     Whoever
    0.12
     trespass
    0.12
     whoever
    0.11
    elig
    0.11
    Activations Density 0.032%

    No Known Activations