© 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. 117337
    Prev
    Next
    INDEX
    Explanations

    words used to describe feelings or express something

    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
     Gos
    -0.11
    cdc
    -0.10
     slap
    -0.09
     Orr
    -0.08
    lev
    -0.08
     Stub
    -0.08
     cin
    -0.08
     comment
    -0.08
    aty
    -0.08
     tat
    -0.08
    POSITIVE LOGITS
    mith
    0.20
     words
    0.17
    worth
    0.16
    /language
    0.15
    words
    0.15
     Words
    0.15
    (words
    0.15
    Words
    0.12
    WORDS
    0.12
    /ph
    0.12
    Activations Density 0.038%

    No Known Activations