© 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. 117504
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude

    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
     vt
    -0.11
    anja
    -0.10
    ?↵↵↵↵↵↵
    -0.10
     Gat
    -0.10
     testim
    -0.10
     Zi
    -0.10
     visita
    -0.10
     excer
    -0.10
    ()?.
    -0.10
    imed
    -0.10
    POSITIVE LOGITS
     mate
    0.12
    zik
    0.11
     allot
    0.10
     buddy
    0.09
     sounding
    0.08
     darling
    0.08
     partner
    0.07
     kid
    0.07
     very
    0.07
     immensely
    0.07
    Activations Density 0.018%

    No Known Activations