© 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. 26140
    Prev
    Next
    INDEX
    Explanations

    can redistribute

    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
     maiden
    -0.09
     Plain
    -0.07
     Kear
    -0.07
    aland
    -0.07
    hou
    -0.07
    emean
    -0.07
     Cov
    -0.07
     bridal
    -0.06
     bore
    -0.06
    NCY
    -0.06
    POSITIVE LOGITS
    unks
    0.12
    ÑģÑĤÑĮ
    0.12
     whatsoever
    0.11
    icate
    0.11
     Crane
    0.11
     Walters
    0.11
    anzi
    0.10
    ва
    0.10
     labels
    0.10
    uger
    0.10
    Activations Density 0.001%

    No Known Activations