© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50538
    Prev
    Next
    INDEX
    Explanations

    patience and being patient

    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
    ovel
    -0.13
    bery
    -0.12
    edic
    -0.12
    orra
    -0.11
    rio
    -0.11
    athe
    -0.11
    spot
    -0.11
    _plain
    -0.11
    uctor
    -0.11
     messy
    -0.11
    POSITIVE LOGITS
     patiently
    0.17
     patience
    0.16
     impatient
    0.15
    pat
    0.10
     waiting
    0.10
     wait
    0.10
     waits
    0.10
     Pat
    0.09
    waiting
    0.09
     waited
    0.09
    Activations Density 0.009%

    No Known Activations