© 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. 115939
    Prev
    Next
    INDEX
    Explanations

    Drivers, Download, Zimbabwe, products, Physics

    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
    errupted
    -0.10
     Seymour
    -0.10
     Becker
    -0.10
    Reviewer
    -0.10
    roperty
    -0.10
    laus
    -0.10
    uta
    -0.10
     prostit
    -0.09
     Sit
    -0.09
    tg
    -0.09
    POSITIVE LOGITS
    chers
    0.08
     filmed
    0.07
     pal
    0.07
    айд
    0.07
     whe
    0.07
     Guards
    0.07
     badly
    0.06
     mond
    0.06
     produ
    0.06
    IFS
    0.06
    Activations Density 0.005%

    No Known Activations