© 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. 47152
    Prev
    Next
    INDEX
    Explanations

    eating and finishing quickly

    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
     nib
    -0.12
     Weird
    -0.10
     Gerr
    -0.10
     Sticky
    -0.10
     penetration
    -0.10
     spreading
    -0.10
     Increment
    -0.10
    ito
    -0.10
    ipping
    -0.10
     incons
    -0.10
    POSITIVE LOGITS
     quickly
    0.12
     entire
    0.12
     quick
    0.12
     contents
    0.11
    aldi
    0.10
    quick
    0.10
     several
    0.10
     half
    0.09
     hurried
    0.09
     rapidly
    0.09
    Activations Density 0.009%

    No Known Activations