© 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. 114282
    Prev
    Next
    INDEX
    Explanations

    any of, and associated

    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
    ERE
    -0.10
    Printing
    -0.10
    eli
    -0.09
    imest
    -0.09
    breadcrumbs
    -0.09
    Chief
    -0.09
    AIT
    -0.09
    ueil
    -0.09
    bounds
    -0.09
    ussen
    -0.09
    POSITIVE LOGITS
     characters
    0.13
     entities
    0.10
    Characters
    0.10
     assets
    0.10
     actors
    0.10
     celebrities
    0.09
     Characters
    0.09
     artwork
    0.09
     gloss
    0.08
     IMM
    0.08
    Activations Density 0.006%

    No Known Activations