© 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. 47138
    Prev
    Next
    INDEX
    Explanations

    medical descriptions precede specific disciplines

    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
    bir
    -0.11
    igin
    -0.10
    ¥
    -0.10
     resultant
    -0.10
     ventilation
    -0.10
     octave
    -0.10
    zek
    -0.10
     Bulg
    -0.10
    ember
    -0.10
     Serg
    -0.10
    POSITIVE LOGITS
     compliant
    0.11
     scared
    0.10
     frightened
    0.09
     backed
    0.08
     panicked
    0.08
     word
    0.08
     terrified
    0.08
     fruit
    0.07
    idon
    0.07
    ichen
    0.07
    Activations Density 0.001%

    No Known Activations