© 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. 47670
    Prev
    Next
    INDEX
    Explanations

    main function or menu

    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
    wise
    -0.09
    .prot
    -0.09
     reck
    -0.08
     bust
    -0.08
    ply
    -0.08
    rub
    -0.08
     recl
    -0.08
     shel
    -0.08
     unint
    -0.08
    regist
    -0.08
    POSITIVE LOGITS
    Secondary
    0.10
    _MINOR
    0.10
     repl
    0.10
    CCA
    0.09
     Secondary
    0.09
     laughing
    0.09
    dpi
    0.09
     crt
    0.09
     subplot
    0.09
     firsthand
    0.09
    Activations Density 0.462%

    No Known Activations