© 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. 30975
    Prev
    Next
    INDEX
    Explanations

    man, train, acial, ish, aboard

    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
     $
    -0.08
     Dew
    -0.08
    αι
    -0.08
    cek
    -0.08
     dew
    -0.07
     <
    -0.07
     spoiler
    -0.07
    649
    -0.07
     decis
    -0.06
     &
    -0.06
    POSITIVE LOGITS
     jong
    0.12
    urator
    0.12
     Followers
    0.11
     utan
    0.11
     Sinn
    0.11
     Democr
    0.11
     scarce
    0.11
    zá
    0.11
     gradu
    0.11
     aboard
    0.11
    Activations Density 0.043%

    No Known Activations