© 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. 92354
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
    itas
    -0.10
     respective
    -0.09
    yr
    -0.09
    estic
    -0.09
    ily
    -0.09
    yle
    -0.09
    nim
    -0.08
     Byron
    -0.08
    medical
    -0.08
    Dims
    -0.08
    POSITIVE LOGITS
    oka
    0.11
     cabinet
    0.11
     Nobel
    0.10
    ucken
    0.10
     Cabinet
    0.10
     dab
    0.10
     fier
    0.10
     ball
    0.10
    /device
    0.10
     grill
    0.09
    Activations Density 0.021%

    No Known Activations