© 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. 111573
    Prev
    Next
    INDEX
    Explanations

    distributed license terms

    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
    -Con
    -0.10
     Schultz
    -0.10
    ÅĦ
    -0.10
    uraa
    -0.10
    indre
    -0.10
    (ne
    -0.10
    caa
    -0.10
     Sharma
    -0.10
     rund
    -0.10
     Face
    -0.10
    POSITIVE LOGITS
    £
    0.16
    ¢
    0.12
    ¤
    0.09
    mani
    0.08
    ÑĮ
    0.08
     tumble
    0.08
     apartheid
    0.07
     Globe
    0.07
    hetto
    0.07
    ({...
    0.07
    Activations Density 0.007%

    No Known Activations