© 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. 31517
    Prev
    Next
    INDEX
    Explanations

    ironic, sarcastic, or satirical 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
     Kon
    -0.10
     Rider
    -0.08
     gob
    -0.08
     Abb
    -0.08
    405
    -0.08
     eccentric
    -0.08
    UD
    -0.08
     McG
    -0.08
     Fraser
    -0.08
     Abbey
    -0.08
    POSITIVE LOGITS
     remarks
    0.16
    /mock
    0.15
     remark
    0.14
     commentary
    0.13
    /comment
    0.13
    -comment
    0.12
     comments
    0.12
     tone
    0.12
     comment
    0.12
     commenting
    0.11
    Activations Density 0.024%

    No Known Activations