© 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. 113560
    Prev
    Next
    INDEX
    Explanations

    biomedical, vacation, online, web development

    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
     itinerary
    -0.12
     timetable
    -0.10
     backdrop
    -0.10
     hike
    -0.10
    osed
    -0.10
     accountant
    -0.10
     roadmap
    -0.09
     schedule
    -0.09
     wrapper
    -0.09
     deadline
    -0.09
    POSITIVE LOGITS
    ism
    0.21
     journalism
    0.21
     politics
    0.20
     activism
    0.19
     filmm
    0.19
    ivism
    0.19
     warfare
    0.18
    anism
    0.18
     photography
    0.18
     technology
    0.18
    Activations Density 1.596%

    No Known Activations