© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 33392
    Prev
    Next
    INDEX
    Explanations

    patience and tolerance

    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
    Not in Any Lists

    No Comments

    Negative Logits
     destruct
    -0.10
     Conv
    -0.10
     streak
    -0.09
    eya
    -0.09
     metam
    -0.09
     rendez
    -0.09
     Rut
    -0.09
     rut
    -0.08
     mu
    -0.08
     moc
    -0.08
    POSITIVE LOGITS
     tolerate
    0.57
     tolerated
    0.54
     tolerance
    0.54
     toler
    0.54
     patience
    0.49
     tolerant
    0.47
    tol
    0.44
     patiently
    0.40
     endured
    0.31
     endure
    0.30
    Activations Density 0.160%

    No Known Activations