© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 51016
    Prev
    Next
    INDEX
    Explanations

    questions about reasons or motivations

    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
    Negative Logits
     Lucky
    -0.11
    airs
    -0.09
     lucky
    -0.09
    oyo
    -0.09
     luck
    -0.09
    IfNeeded
    -0.08
    omat
    -0.08
     dm
    -0.08
    oma
    -0.08
    -scripts
    -0.08
    POSITIVE LOGITS
     motivations
    0.31
     motives
    0.24
     Reasons
    0.22
     motivation
    0.21
     reasons
    0.20
     motiv
    0.19
     motivate
    0.18
     motivating
    0.17
     Mot
    0.17
     motivated
    0.17
    Activations Density 0.053%

    No Known Activations