© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7681
    Prev
    Next
    INDEX
    Explanations

    educational materials and tests

    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
    FRING
    -0.12
     metro
    -0.12
     :::
    -0.12
    ."↵↵↵↵
    -0.12
     emulation
    -0.11
     bottoms
    -0.11
    IFF
    -0.11
     [*
    -0.11
    ãĥ»ãĥ»ãĥ»↵↵
    -0.11
     Glyph
    -0.11
    POSITIVE LOGITS
     textbook
    0.23
     quiz
    0.23
     Quiz
    0.22
     worksheet
    0.22
     exam
    0.20
    Quiz
    0.20
    Worksheet
    0.19
     Homework
    0.19
     homework
    0.19
     Worksheet
    0.19
    Activations Density 2.436%

    No Known Activations