© 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. 32107
    Prev
    Next
    INDEX
    Explanations

    actions or outcomes concerning abstract 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
     skipped
    -0.10
     zig
    -0.09
     Sag
    -0.09
     omitted
    -0.09
    rag
    -0.09
    ())[
    -0.09
    kb
    -0.09
     missed
    -0.09
    rium
    -0.09
     Calder
    -0.09
    POSITIVE LOGITS
     jeopard
    0.14
     prematurely
    0.13
     irre
    0.12
     unnecessarily
    0.12
     Worse
    0.11
     disastr
    0.11
     abruptly
    0.11
    -established
    0.10
     sacrifices
    0.10
     worse
    0.10
    Activations Density 0.185%

    No Known Activations