© 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. 47398
    Prev
    Next
    INDEX
    Explanations

    greetings and physical gestures

    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
     asleep
    -0.10
     bedtime
    -0.10
     Buen
    -0.08
     hare
    -0.08
     sleep
    -0.08
     glory
    -0.08
     conc
    -0.08
     Kaplan
    -0.08
     domestic
    -0.08
     clim
    -0.07
    POSITIVE LOGITS
     greeting
    0.20
     greet
    0.19
     greetings
    0.19
     handshake
    0.19
     greeted
    0.18
     hug
    0.16
     hugged
    0.16
     warmly
    0.13
    /welcome
    0.13
     welcomed
    0.13
    Activations Density 0.028%

    No Known Activations