© 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. 50447
    Prev
    Next
    INDEX
    Explanations

    but, unexpected, sudden conjunction

    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
    ulfilled
    -0.09
    ARIO
    -0.08
    ario
    -0.08
     Gilles
    -0.08
    209
    -0.08
    erno
    -0.08
     brig
    -0.08
    rem
    -0.08
     Fus
    -0.08
    andle
    -0.08
    POSITIVE LOGITS
     unexpectedly
    0.28
     Unexpected
    0.26
    Unexpected
    0.20
     unexpected
    0.20
    unexpected
    0.18
     Suddenly
    0.18
     suddenly
    0.18
     unfortunately
    0.17
    Suddenly
    0.15
     unfore
    0.14
    Activations Density 0.096%

    No Known Activations