© 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. 24955
    Prev
    Next
    INDEX
    Explanations

    genetic information and properties

    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
     Tear
    -0.09
     ens
    -0.09
     Bolton
    -0.09
    Fi
    -0.09
    cover
    -0.09
    resse
    -0.08
    upe
    -0.08
    fram
    -0.08
     refute
    -0.08
    FI
    -0.08
    POSITIVE LOGITS
     unde
    0.11
    anges
    0.09
    âĢ¦↵↵↵↵
    0.09
     geb
    0.09
     Glide
    0.09
    ungi
    0.09
     Princip
    0.09
     overload
    0.09
    pedo
    0.09
     Gus
    0.09
    Activations Density 0.001%

    No Known Activations