© 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. 31328
    Prev
    Next
    INDEX
    Explanations

    speaking or talking

    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
     Niet
    -0.09
     dart
    -0.08
    avn
    -0.08
    elin
    -0.08
     Twig
    -0.08
     Sik
    -0.08
     NEG
    -0.08
     wallpapers
    -0.07
     Dart
    -0.07
     Nexus
    -0.07
    POSITIVE LOGITS
     talking
    0.25
     speaking
    0.23
     reacting
    0.18
     Talking
    0.18
     influencing
    0.17
    Talking
    0.17
     Speaking
    0.16
     showing
    0.15
     causing
    0.15
     expressing
    0.15
    Activations Density 0.144%

    No Known Activations