© 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. 26901
    Prev
    Next
    INDEX
    Explanations

    bizarre moments, stunts, and events

    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
     Hispanics
    -0.09
    thro
    -0.09
     latino
    -0.09
    iola
    -0.08
    ertz
    -0.08
     whispered
    -0.08
     kino
    -0.08
     continental
    -0.08
    isode
    -0.08
     disjoint
    -0.08
    POSITIVE LOGITS
     reportedly
    0.16
     bizarre
    0.15
     stunt
    0.14
     Japan
    0.14
     Guinness
    0.13
     UK
    0.13
     vending
    0.13
     viral
    0.13
     headlines
    0.13
     Japanese
    0.13
    Activations Density 0.538%

    No Known Activations