© 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. 50519
    Prev
    Next
    INDEX
    Explanations

    shapes and surfaces

    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
     curved
    -0.14
     curriculum
    -0.12
     curry
    -0.11
     Curriculum
    -0.11
     Curry
    -0.10
    .Bundle
    -0.10
     deed
    -0.08
    .urls
    -0.08
     Curt
    -0.08
     prince
    -0.08
    POSITIVE LOGITS
     sizes
    0.11
     textures
    0.11
     outright
    0.10
     pint
    0.10
     valleys
    0.10
     jit
    0.10
    azer
    0.10
     bust
    0.10
    rio
    0.10
     terminating
    0.10
    Activations Density 0.021%

    No Known Activations