© 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. 30517
    Prev
    Next
    INDEX
    Explanations

    leaving abruptly or suddenly

    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
     Sag
    -0.11
    iers
    -0.11
     Hoy
    -0.10
    OLA
    -0.10
    cs
    -0.10
     Shades
    -0.10
    ola
    -0.10
    iors
    -0.10
    vik
    -0.10
    rase
    -0.09
    POSITIVE LOGITS
     abruptly
    0.23
     suddenly
    0.21
     sudden
    0.18
     abrupt
    0.17
    Suddenly
    0.14
     Suddenly
    0.14
     unexpectedly
    0.13
     seemingly
    0.12
     frustrating
    0.11
    alto
    0.11
    Activations Density 0.011%

    No Known Activations