© 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. 91055
    Prev
    Next
    INDEX
    Explanations

    player roles in sports and other professions

    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
     Seah
    -0.09
     absolutely
    -0.07
     scaffold
    -0.07
     Bender
    -0.07
     reboot
    -0.07
     sage
    -0.07
     batching
    -0.07
    99
    -0.07
    rr
    -0.07
    818
    -0.07
    POSITIVE LOGITS
     esl
    0.11
     âĨij
    0.11
     Heath
    0.11
     overseas
    0.11
    ifar
    0.11
    fax
    0.10
     Nev
    0.10
    SKU
    0.10
     Goose
    0.10
     Eli
    0.10
    Activations Density 0.054%

    No Known Activations