© 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. 30379
    Prev
    Next
    INDEX
    Explanations

    environment and conditions

    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
    herits
    -0.10
    Wildcard
    -0.10
     verdienen
    -0.09
     fulfill
    -0.09
     dissect
    -0.09
     liter
    -0.09
     еÑģÑĤÑĮ
    -0.09
     OTHERWISE
    -0.09
     communicating
    -0.09
     Milit
    -0.09
    POSITIVE LOGITS
     surrounding
    0.10
     crackdown
    0.10
    framework
    0.10
     Franken
    0.10
     unfairly
    0.09
     Gaw
    0.09
     risk
    0.09
     MB
    0.09
     framework
    0.09
     whisk
    0.09
    Activations Density 0.002%

    No Known Activations