© 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. 50659
    Prev
    Next
    INDEX
    Explanations

    year-old, AM PDT, 040-079

    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
    heck
    -0.09
     rounds
    -0.09
     lil
    -0.09
     Fate
    -0.09
     relativ
    -0.08
     dude
    -0.08
    eu
    -0.08
    shm
    -0.08
     Dude
    -0.08
     Dak
    -0.08
    POSITIVE LOGITS
     seat
    0.11
     marvelous
    0.10
    benh
    0.10
    (of
    0.10
    iot
    0.10
    belongs
    0.10
     itinerary
    0.09
    ==$
    0.09
     deserted
    0.09
     WW
    0.09
    Activations Density 0.004%

    No Known Activations