© 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. 88749
    Prev
    Next
    INDEX
    Explanations

    The neuron detects questions followed by answers

    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
    rea
    -0.11
    ande
    -0.11
    omes
    -0.10
     Lok
    -0.09
    ses
    -0.09
    quire
    -0.09
    MES
    -0.09
    (es
    -0.09
    reas
    -0.08
    erin
    -0.08
    POSITIVE LOGITS
     answer
    0.22
    Answer
    0.21
     Answer
    0.20
    answer
    0.20
    (answer
    0.17
     Hint
    0.17
    hint
    0.17
     Well
    0.17
     certainly
    0.17
     well
    0.17
    Activations Density 0.101%

    No Known Activations