© 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. 114304
    Prev
    Next
    INDEX
    Explanations

    numbers followed by counts or outcomes

    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
    anza
    -0.10
     forums
    -0.09
     Caption
    -0.09
    è¯Ŀ
    -0.09
     celebrities
    -0.09
     rarity
    -0.09
    classes
    -0.09
     Dispatch
    -0.09
     chambers
    -0.09
    que
    -0.09
    POSITIVE LOGITS
     requests
    0.20
     visitors
    0.19
     inquiries
    0.18
     downloads
    0.18
     bookings
    0.17
     traffic
    0.17
     registrations
    0.17
     votes
    0.17
     hits
    0.16
     enquiries
    0.16
    Activations Density 0.324%

    No Known Activations