© 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. 3470
    Prev
    Next
    INDEX
    Explanations

    lists of examples, but

    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
    ires
    -0.11
    mpp
    -0.11
     Roose
    -0.10
     humano
    -0.10
    ede
    -0.10
    Spoiler
    -0.10
    Dyn
    -0.10
    Tcp
    -0.10
    FUNC
    -0.09
    dyn
    -0.09
    POSITIVE LOGITS
    0.10
     thats
    0.09
     ive
    0.09
     wich
    0.09
    ought
    0.08
     isnt
    0.08
     theres
    0.08
    itz
    0.08
    Of
    0.07
    so
    0.07
    Activations Density 0.209%

    No Known Activations