© 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. 112591
    Prev
    Next
    INDEX
    Explanations

    silence or waiting followed by a reply

    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
     Intercept
    -0.10
    holm
    -0.09
     Jah
    -0.09
     Lans
    -0.09
    ACES
    -0.09
    gil
    -0.09
    odom
    -0.09
    ignon
    -0.09
    uci
    -0.09
    UTTON
    -0.09
    POSITIVE LOGITS
     silence
    0.22
     Silence
    0.19
    waiting
    0.17
     Waiting
    0.17
     waiting
    0.16
    Waiting
    0.15
    sil
    0.13
     boredom
    0.13
     timeout
    0.13
     suspense
    0.13
    Activations Density 0.042%

    No Known Activations