© 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. 111420
    Prev
    Next
    INDEX
    Explanations

    ( expression )

    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
    eti
    -0.11
     swinging
    -0.10
     squat
    -0.10
     BFS
    -0.10
    vid
    -0.10
     fraud
    -0.09
     Lam
    -0.09
     impl
    -0.09
     pulver
    -0.09
     bulld
    -0.09
    POSITIVE LOGITS
     feels
    0.15
    Feels
    0.13
     responsiveness
    0.12
     comfortable
    0.11
     silky
    0.11
     sensitive
    0.11
     relaxed
    0.11
     smooth
    0.11
    feel
    0.11
     feel
    0.11
    Activations Density 0.011%

    No Known Activations