© 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. 16829
    Prev
    Next
    INDEX
    Explanations

    choreography/choreographed

    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
     Broadcasting
    -0.10
    ingly
    -0.10
    riv
    -0.09
    ató
    -0.09
     fool
    -0.08
     broadcasting
    -0.08
    imizer
    -0.08
    zelf
    -0.08
    road
    -0.08
     Hof
    -0.08
    POSITIVE LOGITS
    ographed
    0.18
     chore
    0.17
     Chore
    0.15
    ography
    0.14
    opo
    0.13
    scopic
    0.13
     ballet
    0.12
    ographer
    0.11
    /script
    0.11
    manship
    0.10
    Activations Density 0.004%

    No Known Activations