© 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. 18650
    Prev
    Next
    INDEX
    Explanations

    UI icons and selectors

    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
     Damon
    -0.12
     Newman
    -0.10
     hardcoded
    -0.10
     Katz
    -0.10
    ENER
    -0.10
     newline
    -0.10
    ä¸Ģ页
    -0.10
    aggi
    -0.09
     bola
    -0.09
    villa
    -0.09
    POSITIVE LOGITS
     icon
    0.17
     beside
    0.15
     near
    0.15
     âĵĺ
    0.14
     Icon
    0.14
     icons
    0.13
     gear
    0.12
    -icon
    0.12
    located
    0.11
     located
    0.11
    Activations Density 0.431%

    No Known Activations