© 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. 6982
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    —they
    -0.08
    asmine
    -0.07
    —it
    -0.07
     Surf
    -0.07
     surely
    -0.07
    —we
    -0.07
     DEFIN
    -0.07
     gul
    -0.07
     Chim
    -0.07
     âĢ¦↵↵
    -0.07
    POSITIVE LOGITS
    etc
    0.13
     etc
    0.12
     unde
    0.11
     gem
    0.10
     even
    0.10
    Gem
    0.10
    MORE
    0.10
    unas
    0.10
    STA
    0.10
    .dart
    0.10
    Activations Density 0.005%

    No Known Activations