© 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. 47549
    Prev
    Next
    INDEX
    Explanations

    de La, Tissa, acher, ar

    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
     humble
    -0.09
     prolifer
    -0.08
    WithError
    -0.08
    abort
    -0.08
    stk
    -0.07
     wan
    -0.07
     inevitably
    -0.07
     RBI
    -0.07
    ebra
    -0.07
    Clip
    -0.07
    POSITIVE LOGITS
    .waitKey
    0.09
    atat
    0.09
     cog
    0.08
    .GenerationType
    0.08
     subs
    0.08
     divul
    0.08
    zion
    0.08
    .sav
    0.08
     undo
    0.08
    oment
    0.08
    Activations Density 1.250%

    No Known Activations