© 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. 28050
    Prev
    Next
    INDEX
    Explanations

    year, court, mortgage, simulator, controllers

    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
    atu
    -0.10
    hoff
    -0.10
     temporarily
    -0.09
    ayer
    -0.09
    akan
    -0.09
     compared
    -0.09
    avr
    -0.09
    ibal
    -0.09
    ham
    -0.09
    417
    -0.09
    POSITIVE LOGITS
    —with
    0.13
    ROL
    0.10
     ie
    0.09
     uncomp
    0.09
     minus
    0.09
     Ferguson
    0.09
     hs
    0.09
    ogn
    0.09
     cogn
    0.09
     Paula
    0.09
    Activations Density 0.274%

    No Known Activations