© 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. 4633
    Prev
    Next
    INDEX
    Explanations

    personal experience and confusion

    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
     surprise
    -0.15
     surprised
    -0.15
     surprising
    -0.12
     Surprise
    -0.12
     surprises
    -0.11
     unexpectedly
    -0.11
     remorse
    -0.11
     reaction
    -0.11
     realized
    -0.11
    Reaction
    -0.11
    POSITIVE LOGITS
     shrugged
    0.16
     myst
    0.12
     shr
    0.12
     chalk
    0.12
     curiosity
    0.11
     weir
    0.10
     intrigued
    0.10
     ruled
    0.10
     ruling
    0.10
     unsettling
    0.10
    Activations Density 0.164%

    No Known Activations