© 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. 50876
    Prev
    Next
    INDEX
    Explanations

    numbers, ordinals, and place identifiers

    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
     inaug
    -0.12
     greeting
    -0.11
     greet
    -0.11
     Pant
    -0.11
     greetings
    -0.11
     disobed
    -0.10
     domest
    -0.10
     prere
    -0.10
     curs
    -0.09
    Normally
    -0.09
    POSITIVE LOGITS
     silence
    0.14
     sarc
    0.13
     thoughtful
    0.12
     pause
    0.12
     scoff
    0.12
     ponder
    0.12
     incred
    0.11
     Pause
    0.11
     irony
    0.11
     interviewer
    0.11
    Activations Density 0.060%

    No Known Activations