© 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. 3596
    Prev
    Next
    INDEX
    Explanations

    operating properly

    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
     Morton
    -0.11
     ple
    -0.10
     fellows
    -0.10
     pund
    -0.10
     surre
    -0.10
    еÑĢж
    -0.10
     wor
    -0.09
     Walton
    -0.09
    ple
    -0.09
     cri
    -0.09
    POSITIVE LOGITS
     Flake
    0.08
     Amer
    0.08
    ots
    0.08
     Fancy
    0.08
    tees
    0.07
    kal
    0.07
     Trilogy
    0.07
     Lightweight
    0.07
    fern
    0.07
    CAC
    0.07
    Activations Density 0.565%

    No Known Activations