© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    a lot of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    lem
    -0.09
    ift
    -0.09
     Steele
    -0.09
     multic
    -0.09
    lings
    -0.09
     bil
    -0.08
    olf
    -0.08
    iva
    -0.08
     Simmons
    -0.08
     dozens
    -0.08
    POSITIVE LOGITS
     newer
    0.12
    hti
    0.11
     mie
    0.11
    erer
    0.11
    alion
    0.10
     people
    0.10
     sharply
    0.10
     folks
    0.10
     souvent
    0.10
    Ú¯
    0.10
    Activations Density 0.024%

    No Known Activations