© 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. 47778
    Prev
    Next
    INDEX
    Explanations

    date format 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
     Kush
    -0.10
    quare
    -0.10
    ibile
    -0.09
     irres
    -0.09
     Inquiry
    -0.09
     Peyton
    -0.08
    quiry
    -0.08
    ense
    -0.08
     Recap
    -0.08
     Examination
    -0.08
    POSITIVE LOGITS
    olec
    0.11
     ul
    0.09
     bust
    0.09
     ÂŃ
    0.09
    lander
    0.09
     raging
    0.09
     batt
    0.09
     Vill
    0.09
     UL
    0.09
    bred
    0.09
    Activations Density 0.019%

    No Known Activations