© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92630
    Prev
    Next
    INDEX
    Explanations

    SPDX-License-Identifier

    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
    Negative Logits
     ..."↵
    -0.12
    ioned
    -0.11
     ...↵
    -0.11
     {...
    -0.11
     $#
    -0.11
    raq
    -0.11
    legate
    -0.11
    ritz
    -0.11
     ...↵↵
    -0.11
    zon
    -0.11
    POSITIVE LOGITS
     Dios
    0.08
     lifes
    0.08
    argo
    0.08
    -case
    0.07
     Lucas
    0.07
     tent
    0.07
    -E
    0.07
    AINS
    0.07
     Schul
    0.07
    /apple
    0.07
    Activations Density 0.001%

    No Known Activations