© 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. 29696
    Prev
    Next
    INDEX
    Explanations

    howdy, questions, how about

    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
    -il
    -0.08
     bark
    -0.08
     exceeded
    -0.08
     Osw
    -0.08
     flush
    -0.08
     Mann
    -0.07
    767
    -0.07
     Recommended
    -0.07
     Unc
    -0.07
    (ix
    -0.07
    POSITIVE LOGITS
     fam
    0.12
     objection
    0.11
    Views
    0.11
     sounding
    0.11
     sounds
    0.11
     rond
    0.11
     headlines
    0.10
     about
    0.10
     feas
    0.10
     -$
    0.10
    Activations Density 0.073%

    No Known Activations