© 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. 25314
    Prev
    Next
    INDEX
    Explanations

    I followed by a verb

    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
     hear
    -0.14
    hear
    -0.14
     felt
    -0.12
     hoped
    -0.12
     feels
    -0.12
     think
    -0.12
     feel
    -0.11
     gotta
    -0.11
     wonder
    -0.11
    feel
    -0.11
    POSITIVE LOGITS
     allegedly
    0.11
     apparently
    0.10
    /us
    0.10
     supposedly
    0.10
     (
    0.09
     obviously
    0.09
    rtle
    0.09
    oppins
    0.09
     Enlight
    0.09
     visibly
    0.09
    Activations Density 0.067%

    No Known Activations