© 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. 112035
    Prev
    Next
    INDEX
    Explanations

    figure skater or skating

    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
    inator
    -0.09
     fiction
    -0.08
    saida
    -0.08
    smith
    -0.08
    ëł¥
    -0.08
     Mos
    -0.08
    stars
    -0.08
    (er
    -0.08
    agation
    -0.08
     fictional
    -0.08
    POSITIVE LOGITS
    heads
    0.19
    head
    0.18
     skating
    0.14
    -eight
    0.14
    -head
    0.11
    erd
    0.11
    chet
    0.11
     prominently
    0.11
    aux
    0.11
    matic
    0.11
    Activations Density 0.025%

    No Known Activations