© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112211
    Prev
    Next
    INDEX
    Explanations

    glossary, glossy

    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
    ÑĤе
    -0.11
    ement
    -0.11
    ual
    -0.10
    dit
    -0.10
    dzi
    -0.10
    WATCH
    -0.10
    lien
    -0.09
    cox
    -0.09
    ONSE
    -0.09
    iment
    -0.09
    POSITIVE LOGITS
    ary
    0.14
     gloss
    0.11
     cherry
    0.10
    aries
    0.10
    ies
    0.10
    ed
    0.09
    ARY
    0.09
     Finish
    0.09
     finish
    0.09
     surg
    0.09
    Activations Density 0.009%

    No Known Activations