© 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. 8260
    Prev
    Next
    INDEX
    Explanations

    urli.st / urahara / Urho3D

    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
    haven
    -0.11
    iedo
    -0.10
    orget
    -0.10
     professionally
    -0.10
    -educated
    -0.10
    ABEL
    -0.10
     ger
    -0.10
     FX
    -0.10
     Profession
    -0.10
     Consultant
    -0.10
    POSITIVE LOGITS
    cret
    0.08
    inn
    0.08
     Vanderbilt
    0.08
     jaws
    0.08
    ef
    0.08
    kre
    0.08
    kon
    0.07
    ucchini
    0.07
     dict
    0.07
    .kr
    0.07
    Activations Density 0.001%

    No Known Activations