© 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. 3597
    Prev
    Next
    INDEX
    Explanations

    items found or detected

    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
     impunity
    -0.09
     recess
    -0.09
    ëĮĢ
    -0.09
    iny
    -0.09
     deserved
    -0.08
     Separ
    -0.08
     bombard
    -0.08
    overlay
    -0.08
    ACS
    -0.07
     Olivier
    -0.07
    POSITIVE LOGITS
     found
    0.37
    found
    0.31
     Found
    0.30
     discovered
    0.29
    Found
    0.29
    -found
    0.29
     recovered
    0.25
     FOUND
    0.25
     detected
    0.25
    FOUND
    0.24
    Activations Density 1.088%

    No Known Activations