© 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. 15546
    Prev
    Next
    INDEX
    Explanations

    all followed by a noun

    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
     disarm
    -0.09
    olle
    -0.09
     Brendan
    -0.09
     inters
    -0.08
    olon
    -0.08
     Moist
    -0.08
    indle
    -0.08
     belonged
    -0.08
    eced
    -0.08
    /ca
    -0.08
    POSITIVE LOGITS
    owing
    0.10
     Mayer
    0.10
     thanks
    0.10
     types
    0.10
     boils
    0.10
     type
    0.10
    ago
    0.09
    endi
    0.09
    lear
    0.09
     Rights
    0.09
    Activations Density 0.033%

    No Known Activations