© 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. 28891
    Prev
    Next
    INDEX
    Explanations

    dates and numerical figures

    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
     glowing
    -0.07
    Filed
    -0.07
    Sexy
    -0.07
     Tent
    -0.07
     Jess
    -0.07
     sponge
    -0.07
     boyc
    -0.07
    .Pre
    -0.07
    Sid
    -0.07
     accidental
    -0.06
    POSITIVE LOGITS
    sth
    0.10
    /comment
    0.10
     pad
    0.10
     Pad
    0.10
    éri
    0.10
     Ary
    0.10
    pad
    0.10
    ersh
    0.10
    isy
    0.10
     Merry
    0.09
    Activations Density 0.635%

    No Known Activations