© 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. 117305
    Prev
    Next
    INDEX
    Explanations

    amount of torque

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cupid
    -0.09
     protr
    -0.09
     outward
    -0.09
     Fla
    -0.09
    mund
    -0.08
     onboard
    -0.08
     Bernstein
    -0.08
    nbsp
    -0.08
     ***↵
    -0.08
     Morm
    -0.08
    POSITIVE LOGITS
     massage
    0.10
     Vu
    0.09
    ospel
    0.09
     crack
    0.09
     gutter
    0.09
     insanity
    0.09
     Crack
    0.09
     stupidity
    0.09
     wich
    0.09
    _PS
    0.08
    Activations Density 0.003%

    No Known Activations