© 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. 26205
    Prev
    Next
    INDEX
    Explanations

    human or animal sculpture/figurine

    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
     painters
    -0.12
     painter
    -0.12
    paint
    -0.11
     stripes
    -0.11
     paintings
    -0.11
     paint
    -0.10
     laid
    -0.10
     diagrams
    -0.10
     graf
    -0.10
     rectangles
    -0.10
    POSITIVE LOGITS
     stat
    0.16
     figur
    0.14
     bust
    0.14
     whims
    0.13
     squat
    0.12
     sculpture
    0.12
    /stat
    0.12
     sculptures
    0.11
     Bust
    0.11
     statute
    0.11
    Activations Density 0.329%

    No Known Activations