© 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. 7220
    Prev
    Next
    INDEX
    Explanations

    paste into code

    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
     MacDonald
    -0.11
    ë¡Ŀ
    -0.10
    sto
    -0.10
     Orig
    -0.10
     Beg
    -0.10
    eba
    -0.10
     mund
    -0.09
    _elt
    -0.09
     slightest
    -0.09
     Sho
    -0.09
    POSITIVE LOGITS
     sor
    0.08
     dd
    0.08
    antee
    0.08
    ninger
    0.08
     Emin
    0.08
    inery
    0.08
     booming
    0.08
    atat
    0.08
     bust
    0.08
     batter
    0.07
    Activations Density 0.037%

    No Known Activations