© 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. 26768
    Prev
    Next
    INDEX
    Explanations

    code imports and definitions

    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
     grop
    -0.10
     Dahl
    -0.09
    zem
    -0.09
     Frontier
    -0.09
     overlay
    -0.09
     unfinished
    -0.09
    enis
    -0.09
     Supreme
    -0.09
     gum
    -0.08
    inch
    -0.08
    POSITIVE LOGITS
     zeit
    0.10
     ascent
    0.10
     briefly
    0.10
     Inject
    0.10
     upward
    0.10
     Barrett
    0.10
     upright
    0.09
     Toolbox
    0.09
     Wyn
    0.09
     Craw
    0.09
    Activations Density 0.034%

    No Known Activations