© 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. 34136
    Prev
    Next
    INDEX
    Explanations

    reporting data or information

    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
     generosity
    -0.11
     kindness
    -0.11
     publicly
    -0.10
     tweeted
    -0.10
    DATED
    -0.10
    åħ¬
    -0.10
     publicity
    -0.10
    "@
    -0.10
    elig
    -0.10
     Corner
    -0.09
    POSITIVE LOGITS
     report
    0.51
     reports
    0.48
     reporting
    0.45
     Report
    0.43
    report
    0.40
     Reports
    0.40
    -report
    0.39
     Reporting
    0.37
     REPORT
    0.37
    Report
    0.37
    Activations Density 0.365%

    No Known Activations