© 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. 31218
    Prev
    Next
    INDEX
    Explanations

    copies, documents, information

    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
    Built
    -0.10
    built
    -0.10
     built
    -0.10
     Georges
    -0.10
     Hancock
    -0.09
    Bookmark
    -0.09
     gri
    -0.09
     Built
    -0.09
     arbitrarily
    -0.09
     tucked
    -0.09
    POSITIVE LOGITS
     copies
    0.34
     copy
    0.25
     Copies
    0.25
    copies
    0.23
     documents
    0.22
    .copy
    0.19
     photographs
    0.18
     tapes
    0.18
     Copy
    0.18
    copy
    0.18
    Activations Density 0.921%

    No Known Activations