© 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. 92542
    Prev
    Next
    INDEX
    Explanations

    tolerance to variations or conditions

    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
    port
    -0.09
     Doming
    -0.09
    isle
    -0.09
     solidarity
    -0.09
    aket
    -0.09
     jeopardy
    -0.09
    perc
    -0.09
     jaws
    -0.09
    idor
    -0.09
     adequ
    -0.09
    POSITIVE LOGITS
     deviations
    0.14
     mistakes
    0.14
     ambiguity
    0.13
     tolerate
    0.13
     toler
    0.13
     differences
    0.13
     intolerance
    0.13
     diversity
    0.13
     intoler
    0.12
     deviation
    0.12
    Activations Density 0.103%

    No Known Activations