© 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. 48923
    Prev
    Next
    INDEX
    Explanations

    waving or waved

    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
     unm
    -0.11
     vel
    -0.10
    ression
    -0.09
    uku
    -0.09
     Vel
    -0.09
    mate
    -0.09
    ç¢
    -0.09
     Cham
    -0.09
    aba
    -0.09
     bunk
    -0.09
    POSITIVE LOGITS
     flagged
    0.17
     flag
    0.17
     flags
    0.16
     waving
    0.16
     goodbye
    0.16
    -flag
    0.14
     Flag
    0.14
     waved
    0.14
     wand
    0.13
     enticing
    0.13
    Activations Density 0.029%

    No Known Activations