© 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. 50689
    Prev
    Next
    INDEX
    Explanations

    contact details or opening times

    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
     Hoy
    -0.10
    iam
    -0.08
    LEASE
    -0.08
     Mojo
    -0.08
    stre
    -0.08
    _advanced
    -0.08
     Burton
    -0.08
    Continue
    -0.08
    anes
    -0.08
     owe
    -0.08
    POSITIVE LOGITS
     pie
    0.10
     Bron
    0.09
     Pie
    0.09
     intact
    0.09
    resse
    0.09
    /bus
    0.09
    APA
    0.09
     Foley
    0.09
     Miranda
    0.09
     devis
    0.09
    Activations Density 0.009%

    No Known Activations