© 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. 112749
    Prev
    Next
    INDEX
    Explanations

    dance and related activities

    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
     chic
    -0.08
     blot
    -0.08
    vana
    -0.08
     compet
    -0.07
    ibles
    -0.07
    oes
    -0.07
    _IV
    -0.07
    okies
    -0.07
    antu
    -0.07
     CT
    -0.07
    POSITIVE LOGITS
     danced
    0.18
     dance
    0.15
     dancers
    0.14
    dance
    0.14
     dancing
    0.13
     dances
    0.13
     Dancing
    0.13
     dancer
    0.13
     Ballet
    0.12
     Dance
    0.12
    Activations Density 0.002%

    No Known Activations