© 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. 5796
    Prev
    Next
    INDEX
    Explanations

    file is

    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
    uzzi
    -0.08
     departed
    -0.08
     nas
    -0.08
    493
    -0.08
     Criteria
    -0.08
     lacking
    -0.07
     stif
    -0.07
     Ann
    -0.07
    ovich
    -0.07
     cri
    -0.07
    POSITIVE LOGITS
     Cout
    0.12
    arme
    0.11
    ird
    0.11
    ä»ĭ
    0.11
    lers
    0.10
     Sommer
    0.10
    erd
    0.10
     dint
    0.10
    orge
    0.10
    ented
    0.10
    Activations Density 0.001%

    No Known Activations