© 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. 24948
    Prev
    Next
    INDEX
    Explanations

    reported words and suffixes

    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
    ernel
    -0.09
     ultr
    -0.09
    ve
    -0.08
    yla
    -0.08
     Dw
    -0.08
    ischen
    -0.08
     Dudley
    -0.08
    /stream
    -0.08
     Fus
    -0.08
     craft
    -0.07
    POSITIVE LOGITS
    edly
    0.18
    /report
    0.16
     report
    0.15
    ers
    0.15
     Report
    0.15
    spam
    0.14
     reporters
    0.14
    bug
    0.13
     Abuse
    0.13
    oire
    0.13
    Activations Density 0.012%

    No Known Activations