© 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. 90217
    Prev
    Next
    INDEX
    Explanations

    intensifiers with emotional states

    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
    rup
    -0.11
     detrimental
    -0.11
     freely
    -0.11
     humiliating
    -0.11
     unsustainable
    -0.10
    mites
    -0.10
     mö
    -0.10
     harmful
    -0.10
     willingly
    -0.10
    igne
    -0.10
    POSITIVE LOGITS
     intrigued
    0.18
     excited
    0.17
     intrigue
    0.17
     upset
    0.17
     impressed
    0.17
     shocked
    0.16
     surprised
    0.16
     shock
    0.16
     disturbed
    0.16
     confused
    0.15
    Activations Density 0.094%

    No Known Activations