© 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. 13849
    Prev
    Next
    INDEX
    Explanations

    public, strong, slow, new, deadly, whopping, assessment

    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
     phenomenon
    -0.10
     Newly
    -0.10
     Mens
    -0.10
     annually
    -0.09
     phenomena
    -0.09
    yan
    -0.09
     sentiments
    -0.09
    mani
    -0.09
     RESP
    -0.09
     perennial
    -0.09
    POSITIVE LOGITS
     meaningful
    0.10
     extensive
    0.10
    ?):
    0.10
     robust
    0.09
     carefully
    0.09
    /cms
    0.09
     explor
    0.09
     spectacular
    0.09
     lengthy
    0.09
     extended
    0.09
    Activations Density 0.375%

    No Known Activations