© 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. 7166
    Prev
    Next
    INDEX
    Explanations

    HTML, JavaScript, data, lists

    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
    dish
    -0.10
    Likes
    -0.09
    oplay
    -0.09
    ordin
    -0.09
     sez
    -0.09
     Welch
    -0.09
    neh
    -0.09
    aida
    -0.09
    iro
    -0.08
    ellig
    -0.08
    POSITIVE LOGITS
    Portal
    0.09
    itat
    0.09
     foil
    0.08
    velle
    0.08
     Pastor
    0.08
     pink
    0.08
    Pink
    0.08
     livest
    0.08
     unf
    0.08
     trav
    0.08
    Activations Density 0.012%

    No Known Activations