© 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. 18314
    Prev
    Next
    INDEX
    Explanations

    orientational, inflammation, or noun endings

    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
    bru
    -0.09
     conduct
    -0.08
     bru
    -0.08
    olen
    -0.07
     conspir
    -0.07
     major
    -0.07
     bumper
    -0.07
     toll
    -0.07
     rent
    -0.07
     tremendous
    -0.07
    POSITIVE LOGITS
    ysize
    0.10
     indeb
    0.10
    redi
    0.09
    actor
    0.09
    cfg
    0.09
    iability
    0.09
    crate
    0.09
    quet
    0.09
     Seymour
    0.09
     Holt
    0.09
    Activations Density 2.392%

    No Known Activations