© 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. 28198
    Prev
    Next
    INDEX
    Explanations

    scientific assays and characterization

    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
    /not
    -0.12
     irritated
    -0.12
     blob
    -0.12
     irrit
    -0.12
     goo
    -0.11
     substance
    -0.11
     readings
    -0.11
     crit
    -0.11
     literal
    -0.11
     medically
    -0.11
    POSITIVE LOGITS
     characterization
    0.15
     pret
    0.13
     (âĪ
    0.12
     assays
    0.11
     elucid
    0.11
     quant
    0.11
     novel
    0.10
    .Experimental
    0.10
     investigated
    0.10
     herein
    0.10
    Activations Density 27.262%

    No Known Activations