© 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. 34137
    Prev
    Next
    INDEX
    Explanations

    questioning statements or requests

    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
    Define
    -0.10
     handic
    -0.10
    trys
    -0.10
    hud
    -0.10
     Describe
    -0.09
     jpeg
    -0.09
     Define
    -0.09
     define
    -0.09
     procur
    -0.08
    AI
    -0.08
    POSITIVE LOGITS
     sentence
    0.10
     sentiment
    0.10
     rewriting
    0.10
     sentences
    0.09
     Above
    0.09
     Rew
    0.09
     fused
    0.09
     rewrite
    0.09
     above
    0.09
     Brewer
    0.09
    Activations Density 0.292%

    No Known Activations