© 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. 47233
    Prev
    Next
    INDEX
    Explanations

    labeled, dubbed, coined, designated, branded

    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
     Boone
    -0.10
     quand
    -0.10
    ando
    -0.09
    andel
    -0.09
     ubiqu
    -0.09
    OO
    -0.09
     Repos
    -0.09
    ione
    -0.09
    iba
    -0.09
    ancia
    -0.08
    POSITIVE LOGITS
     unfit
    0.13
     as
    0.13
     accordingly
    0.11
     quits
    0.11
    /tag
    0.11
     “
    0.11
     appropriately
    0.10
     worthy
    0.10
     ‘
    0.09
     ineligible
    0.09
    Activations Density 0.219%

    No Known Activations