© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31364
    Prev
    Next
    INDEX
    Explanations

    leg starter

    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
     wrist
    -0.10
    aty
    -0.08
     wrench
    -0.08
     occupational
    -0.08
    Controllers
    -0.08
     shoe
    -0.07
    Joined
    -0.07
     Shoe
    -0.07
    uckles
    -0.07
     wheel
    -0.07
    POSITIVE LOGITS
     Spacer
    0.11
     Stard
    0.11
     tad
    0.10
    (L
    0.10
    (IL
    0.10
    OrCreate
    0.09
     Trem
    0.09
     staffer
    0.09
     Fres
    0.09
    arme
    0.09
    Activations Density 0.050%

    No Known Activations