© 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. 113091
    Prev
    Next
    INDEX
    Explanations

    pauses, sighs, or smiles

    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
    adin
    -0.09
    assa
    -0.08
    AIM
    -0.08
    reur
    -0.08
    ingo
    -0.08
    /project
    -0.07
    vil
    -0.07
     Ãĥ
    -0.07
     AIM
    -0.07
    evice
    -0.07
    POSITIVE LOGITS
     paused
    0.27
     pause
    0.27
     pauses
    0.26
     Pause
    0.23
     sighed
    0.22
     smiled
    0.22
     smirk
    0.22
    pause
    0.22
     sigh
    0.21
     grinned
    0.21
    Activations Density 0.090%

    No Known Activations