© 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. 18741
    Prev
    Next
    INDEX
    Explanations

    you can control or discover

    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
     offline
    -0.10
     Standing
    -0.09
     extrad
    -0.09
    /apps
    -0.08
     back
    -0.08
     applications
    -0.08
    oucher
    -0.08
     jr
    -0.08
     Fisher
    -0.08
    Converted
    -0.08
    POSITIVE LOGITS
     connect
    0.14
     browse
    0.14
     interact
    0.13
     join
    0.12
     connects
    0.12
     enjoy
    0.11
     Browse
    0.11
     easily
    0.11
     Join
    0.11
     interacting
    0.11
    Activations Density 0.087%

    No Known Activations