© 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. 7148
    Prev
    Next
    INDEX
    Explanations

    Krist names

    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
     Shade
    -0.11
     Nem
    -0.11
    lage
    -0.11
    GLE
    -0.11
     Ele
    -0.11
     heavenly
    -0.10
    oline
    -0.10
     Reached
    -0.10
     Nie
    -0.10
     teng
    -0.10
    POSITIVE LOGITS
     enter
    0.11
    eron
    0.09
     Enter
    0.08
    pla
    0.08
    Enter
    0.08
     select
    0.08
    pas
    0.08
     odom
    0.08
    eri
    0.08
    nuts
    0.08
    Activations Density 0.001%

    No Known Activations