© 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. 6842
    Prev
    Next
    INDEX
    Explanations

    accidental outcomes

    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
     accidental
    -0.13
     unwitting
    -0.11
     accidentally
    -0.11
     unintended
    -0.11
     accident
    -0.11
     unintention
    -0.11
     Accident
    -0.11
     accidents
    -0.10
     inadvert
    -0.10
     inex
    -0.10
    POSITIVE LOGITS
     (?)
    0.19
    /un
    0.16
    -on
    0.15
    /il
    0.14
    /on
    0.13
    /not
    0.12
    -On
    0.12
    /in
    0.12
    /con
    0.12
    /random
    0.12
    Activations Density 0.009%

    No Known Activations