© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16533
    Prev
    Next
    INDEX
    Explanations

    indifference or being forgiven

    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
     suddenly
    -0.12
     unexpectedly
    -0.10
     sudden
    -0.10
     abruptly
    -0.10
     elegant
    -0.10
     potentially
    -0.10
     unexpected
    -0.09
     balk
    -0.09
     ordinarily
    -0.09
     Catal
    -0.09
    POSITIVE LOGITS
     forgiving
    0.25
     harmless
    0.24
     tolerant
    0.20
     indifferent
    0.19
     impunity
    0.19
     already
    0.19
     forgiven
    0.17
     irrelevant
    0.17
     negligible
    0.17
     indifference
    0.17
    Activations Density 0.125%

    No Known Activations