© 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. 16782
    Prev
    Next
    INDEX
    Explanations

    library resources and services

    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
     archive
    -0.13
    -archive
    -0.12
     archives
    -0.12
     replay
    -0.12
    archive
    -0.11
     archived
    -0.11
     scrolls
    -0.10
     penned
    -0.10
     Vaults
    -0.10
     Archive
    -0.10
    POSITIVE LOGITS
     libr
    0.12
     consort
    0.11
     overdue
    0.11
     circulation
    0.11
     patrons
    0.11
     publicity
    0.11
     bibli
    0.10
     patron
    0.10
     Lib
    0.10
     Shel
    0.10
    Activations Density 0.633%

    No Known Activations