© 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. 31272
    Prev
    Next
    INDEX
    Explanations

    case names and proper nouns

    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
     yak
    -0.09
    fx
    -0.09
    y
    -0.08
    edly
    -0.08
    idel
    -0.08
    kf
    -0.08
     Polly
    -0.08
     ringing
    -0.08
    ->__
    -0.08
    =y
    -0.08
    POSITIVE LOGITS
    logue
    0.11
     Trilogy
    0.11
     Forge
    0.10
    lc
    0.09
     Err
    0.09
     ®
    0.09
    REV
    0.09
     Sz
    0.09
     Appendix
    0.09
    ®
    0.09
    Activations Density 0.008%

    No Known Activations