© 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. 92570
    Prev
    Next
    INDEX
    Explanations

    currency followed by numbers

    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
     suspended
    -0.11
     suspension
    -0.09
     subs
    -0.09
     Nap
    -0.09
     unl
    -0.09
     readily
    -0.08
    -tip
    -0.08
    vest
    -0.08
    IFO
    -0.08
     servicing
    -0.08
    POSITIVE LOGITS
    rees
    0.10
    Addon
    0.10
     strictly
    0.10
    Accent
    0.10
     elimination
    0.10
    counts
    0.09
    fault
    0.09
     Flake
    0.09
     leopard
    0.09
    haus
    0.09
    Activations Density 0.016%

    No Known Activations