© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49575
    Prev
    Next
    INDEX
    Explanations

    operations, tasks, behavior, errors, communication, activities

    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
     occurring
    -0.10
    Performed
    -0.10
     Kirk
    -0.10
     Pike
    -0.10
     MIS
    -0.09
     happening
    -0.09
    547
    -0.09
     viên
    -0.09
    uer
    -0.09
     Undert
    -0.09
    POSITIVE LOGITS
     outdoors
    0.13
     autonom
    0.13
     together
    0.12
     willingly
    0.12
     efficiently
    0.11
     aloud
    0.11
     anonymously
    0.11
     intermitt
    0.11
     concurrently
    0.11
     flaw
    0.11
    Activations Density 0.461%

    No Known Activations