© 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. 7090
    Prev
    Next
    INDEX
    Explanations

    unexpected or unintended events

    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
     defensively
    -0.10
    /rc
    -0.10
     unspecified
    -0.10
    legen
    -0.10
     sez
    -0.09
    ucken
    -0.09
     whichever
    -0.09
     countered
    -0.09
    airo
    -0.09
     obviously
    -0.09
    POSITIVE LOGITS
     unwitting
    0.20
     unexpected
    0.19
     events
    0.18
     unfore
    0.18
     unexpectedly
    0.17
     unintention
    0.17
     inadvert
    0.17
    Unexpected
    0.16
     Unexpected
    0.16
     unintended
    0.16
    Activations Density 0.125%

    No Known Activations