© 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. 16010
    Prev
    Next
    INDEX
    Explanations

    convulsions, contractions, twitching

    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
     nurturing
    -0.09
     cassette
    -0.09
     mindfulness
    -0.09
    .blob
    -0.08
     Clar
    -0.08
     lend
    -0.08
    hamster
    -0.08
    infile
    -0.08
     nurt
    -0.08
    [:]
    -0.08
    POSITIVE LOGITS
     twitch
    0.35
     trem
    0.32
     spas
    0.32
     conv
    0.31
     Twitch
    0.28
     involuntary
    0.27
     shaking
    0.26
     trembling
    0.25
     shake
    0.24
     shakes
    0.24
    Activations Density 0.203%

    No Known Activations