© 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. 111557
    Prev
    Next
    INDEX
    Explanations

    positive feelings or sensations

    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
     carefully
    -0.13
     diligently
    -0.12
     Cunning
    -0.10
     taboo
    -0.10
     cunning
    -0.10
     secretive
    -0.10
     diligent
    -0.10
     frowned
    -0.09
     kindly
    -0.09
     etiquette
    -0.09
    POSITIVE LOGITS
     unforgettable
    0.21
     exhilar
    0.19
     overwhelmed
    0.19
     satisfaction
    0.19
     bliss
    0.18
     enjoyment
    0.18
     sensations
    0.18
     dizzy
    0.18
     feeling
    0.17
     sensation
    0.17
    Activations Density 0.197%

    No Known Activations