© 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. 28689
    Prev
    Next
    INDEX
    Explanations

    unexpectedly

    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
     smiles
    -0.13
     sigh
    -0.12
    itta
    -0.12
     smile
    -0.11
    isan
    -0.11
    ims
    -0.11
    isha
    -0.10
     translucent
    -0.10
     crying
    -0.10
     limp
    -0.10
    POSITIVE LOGITS
     unexpectedly
    0.17
     unexpected
    0.16
     suddenly
    0.12
     sudden
    0.11
     Unexpected
    0.11
     unfamiliar
    0.11
    unexpected
    0.11
     Suddenly
    0.11
     successfully
    0.10
    Unexpected
    0.10
    Activations Density 0.016%

    No Known Activations