© 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. 117622
    Prev
    Next
    INDEX
    Explanations

    status of items

    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
     metros
    -0.11
    iona
    -0.10
     Aless
    -0.10
    enko
    -0.10
     meteor
    -0.10
    ож
    -0.10
    anko
    -0.10
    nev
    -0.09
    nge
    -0.09
     femin
    -0.09
    POSITIVE LOGITS
     categorized
    0.09
     Tanner
    0.08
     crud
    0.07
     scored
    0.07
     alphanumeric
    0.07
     weighing
    0.07
     costing
    0.07
     weighting
    0.07
     rated
    0.07
     categor
    0.07
    Activations Density 0.009%

    No Known Activations