© 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. 18547
    Prev
    Next
    INDEX
    Explanations

    so and adjectives of extreme quality

    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
     very
    -0.09
     Illustrated
    -0.08
     quite
    -0.08
    uran
    -0.08
     somewhat
    -0.08
    very
    -0.08
    amil
    -0.07
     Bij
    -0.07
    Very
    -0.07
    essler
    -0.07
    POSITIVE LOGITS
    oth
    0.16
    -so
    0.14
     sufficiently
    0.13
    ooo
    0.12
    -called
    0.12
    ley
    0.12
    jour
    0.12
    LEY
    0.12
    oooooooo
    0.11
    oooo
    0.11
    Activations Density 0.042%

    No Known Activations