© 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. 87943
    Prev
    Next
    INDEX
    Explanations

    accepting submissions or applications

    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
     Millions
    -0.10
    pag
    -0.09
    lam
    -0.08
     confronting
    -0.08
    apos
    -0.08
     Webb
    -0.08
     intrinsic
    -0.08
    iators
    -0.08
     conform
    -0.08
     marching
    -0.08
    POSITIVE LOGITS
     open
    0.27
     accepting
    0.26
     accepts
    0.21
     solicit
    0.21
    open
    0.20
     solic
    0.19
     available
    0.19
     OPEN
    0.18
     accept
    0.18
     registrations
    0.18
    Activations Density 0.512%

    No Known Activations