© 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. 31599
    Prev
    Next
    INDEX
    Explanations

    comparative advantages or preferences

    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
     brit
    -0.11
    ertz
    -0.10
     invert
    -0.10
     attractive
    -0.10
     fascinating
    -0.10
    cee
    -0.10
     rarity
    -0.10
    FO
    -0.10
     affordable
    -0.09
     enticing
    -0.09
    POSITIVE LOGITS
     fewer
    0.14
     cleaner
    0.12
     easier
    0.11
     nicer
    0.10
     better
    0.10
    otherwise
    0.10
     Better
    0.10
     otherwise
    0.10
     simpler
    0.10
     clearer
    0.09
    Activations Density 0.121%

    No Known Activations