© 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. 26267
    Prev
    Next
    INDEX
    Explanations

    small quantity or degree

    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
     sorry
    -0.07
     various
    -0.07
    SEE
    -0.07
    ante
    -0.07
    nas
    -0.07
    pped
    -0.07
     somehow
    -0.07
     corp
    -0.06
     ways
    -0.06
    ihan
    -0.06
    POSITIVE LOGITS
     exposure
    0.14
     jud
    0.14
     dab
    0.13
     doses
    0.13
     tweaking
    0.13
     moderate
    0.13
     inconvenience
    0.13
    omal
    0.12
     tweaks
    0.12
     Exposure
    0.12
    Activations Density 0.067%

    No Known Activations