© 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. 13896
    Prev
    Next
    INDEX
    Explanations

    feeling grateful and thankful

    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
     aprox
    -0.10
     vind
    -0.10
     skys
    -0.10
     Prediction
    -0.09
     Reputation
    -0.09
    pei
    -0.09
     Rangers
    -0.09
     prediction
    -0.09
     Compatibility
    -0.09
     amateur
    -0.09
    POSITIVE LOGITS
     gratitude
    0.50
     grateful
    0.49
     thankful
    0.44
     thanking
    0.38
     grate
    0.36
     thank
    0.36
     thanked
    0.34
     apprec
    0.32
     appreciation
    0.31
     Thank
    0.30
    Activations Density 0.192%

    No Known Activations