© 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. 24967
    Prev
    Next
    INDEX
    Explanations

    list of things

    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
     statues
    -0.10
     gangs
    -0.10
     Insets
    -0.10
     vegetables
    -0.09
     diseases
    -0.09
    ikk
    -0.09
     vegetable
    -0.09
     illnesses
    -0.09
     gases
    -0.09
     Bib
    -0.09
    POSITIVE LOGITS
     resources
    0.14
     stuff
    0.13
     media
    0.13
     materials
    0.13
     entities
    0.13
     items
    0.12
     anything
    0.12
     Items
    0.12
    anything
    0.12
    -resources
    0.11
    Activations Density 1.018%

    No Known Activations