© 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. 16272
    Prev
    Next
    INDEX
    Explanations

    dancing or distributed

    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
    oops
    -0.11
    oles
    -0.10
    -manager
    -0.10
     mold
    -0.10
    ç»ı
    -0.10
     trusting
    -0.10
     circulating
    -0.10
    ULK
    -0.09
    rat
    -0.09
     collapsing
    -0.09
    POSITIVE LOGITS
     danced
    0.14
     dance
    0.14
     dances
    0.12
     dancing
    0.11
     delight
    0.11
    dance
    0.10
     dancer
    0.10
     fingers
    0.10
     fingertips
    0.10
     Dance
    0.09
    Activations Density 0.004%

    No Known Activations