© 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. 25267
    Prev
    Next
    INDEX
    Explanations

    sudden onset

    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
     responders
    -0.11
     Chambers
    -0.11
    bru
    -0.11
     resposta
    -0.10
     keyed
    -0.10
     seeing
    -0.10
     stressing
    -0.10
     pleading
    -0.10
    -response
    -0.10
     retaliation
    -0.10
    POSITIVE LOGITS
     suddenly
    0.15
     preceded
    0.13
     followed
    0.12
     Suddenly
    0.12
     abruptly
    0.11
     abrupt
    0.11
     shortly
    0.11
     momentarily
    0.11
     sudden
    0.11
     preceding
    0.10
    Activations Density 0.031%

    No Known Activations