© 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. 13837
    Prev
    Next
    INDEX
    Explanations

    report on statistics percentages

    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
     correl
    -0.10
    eten
    -0.09
     Mans
    -0.09
     arguably
    -0.09
     correlated
    -0.09
     whats
    -0.09
     prolific
    -0.09
     correlations
    -0.08
     Claude
    -0.08
     correlates
    -0.08
    POSITIVE LOGITS
     unspecified
    0.17
     respondent
    0.17
     (%)
    0.16
     hass
    0.14
     miscellaneous
    0.14
     respondents
    0.13
     oneself
    0.13
    /Dk
    0.13
     “[
    0.13
     (%
    0.13
    Activations Density 0.426%

    No Known Activations