© 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. 32002
    Prev
    Next
    INDEX
    Explanations

    affirmative responses like "Yeah", "Well", "Absolutely"

    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
     Gol
    -0.10
     Ting
    -0.10
    anel
    -0.09
     pic
    -0.09
    .postMessage
    -0.09
    ffer
    -0.09
     dine
    -0.08
     DAM
    -0.08
    _ff
    -0.08
    .upload
    -0.08
    POSITIVE LOGITS
     Yeah
    0.19
     yeah
    0.18
    Yeah
    0.17
     Well
    0.17
    yeah
    0.16
     Absolutely
    0.15
     definitely
    0.15
    Absolutely
    0.15
    Well
    0.15
     absolutely
    0.14
    Activations Density 0.059%

    No Known Activations