© 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. 50995
    Prev
    Next
    INDEX
    Explanations

    should I

    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
     sufficiently
    -0.13
     correctly
    -0.12
     adequately
    -0.11
    992
    -0.11
     enough
    -0.11
     adequate
    -0.10
     sufficient
    -0.10
     properly
    -0.10
    cope
    -0.10
     duly
    -0.10
    POSITIVE LOGITS
     bother
    0.17
     worry
    0.16
     concern
    0.13
     bothered
    0.13
     worried
    0.13
     worrying
    0.12
     continue
    0.12
     Continue
    0.12
     preocup
    0.12
     bothering
    0.11
    Activations Density 0.103%

    No Known Activations