© 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. 29093
    Prev
    Next
    INDEX
    Explanations

    board, graph, Court, stream, cell

    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
    frag
    -0.11
    ori
    -0.10
     unf
    -0.10
     extinction
    -0.09
     disposition
    -0.09
     dictated
    -0.09
    DP
    -0.09
    coat
    -0.09
     Kis
    -0.08
     Trails
    -0.08
    POSITIVE LOGITS
    ting
    0.12
     cling
    0.09
     finde
    0.09
     gou
    0.09
     unt
    0.09
    ®
    0.09
    te
    0.09
    bing
    0.09
    tem
    0.09
     equ
    0.09
    Activations Density 0.001%

    No Known Activations