© 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. 49039
    Prev
    Next
    INDEX
    Explanations

    reason or motivation

    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
    lest
    -0.10
     blaming
    -0.10
     åķ
    -0.10
     Murray
    -0.10
    asel
    -0.09
    ittle
    -0.09
    ahn
    -0.09
    olare
    -0.09
     unl
    -0.09
     Adaptive
    -0.09
    POSITIVE LOGITS
     reason
    0.41
     reasons
    0.38
     motivation
    0.33
     motiv
    0.32
     motivations
    0.31
     Reasons
    0.30
     motivating
    0.30
     justification
    0.30
     motivate
    0.28
    reason
    0.28
    Activations Density 0.289%

    No Known Activations