© 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. 18496
    Prev
    Next
    INDEX
    Explanations

    parts of words

    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
     McCarthy
    -0.10
     Crimson
    -0.10
     Braun
    -0.09
    LIK
    -0.09
    hores
    -0.09
    nze
    -0.08
     Branch
    -0.08
     Peninsula
    -0.08
    .segment
    -0.08
     COPYRIGHT
    -0.08
    POSITIVE LOGITS
    ettes
    0.11
     Fle
    0.09
    '_
    0.09
    -catching
    0.08
     himself
    0.07
     singly
    0.07
     filler
    0.07
    Hack
    0.07
     lite
    0.07
     substitute
    0.07
    Activations Density 2.333%

    No Known Activations