© 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. 48678
    Prev
    Next
    INDEX
    Explanations

    sarcasm or mocking tone

    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
    ilan
    -0.12
    -errors
    -0.10
    erge
    -0.10
     confidential
    -0.10
     Conf
    -0.10
    heim
    -0.10
    iry
    -0.10
     explan
    -0.09
    ASK
    -0.09
    ndef
    -0.09
    POSITIVE LOGITS
     sarc
    0.54
     sarcast
    0.47
     mocking
    0.25
     mock
    0.25
     mockery
    0.24
    sar
    0.23
     ironic
    0.23
     mocked
    0.21
     ironically
    0.20
     sar
    0.19
    Activations Density 0.042%

    No Known Activations