© 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. 46539
    Prev
    Next
    INDEX
    Explanations

    accidents and accidental 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
     Bray
    -0.09
    uto
    -0.09
    ì¦
    -0.09
     Tina
    -0.08
    grounds
    -0.08
    ths
    -0.08
     Ballard
    -0.08
     precis
    -0.08
    utos
    -0.08
    ING
    -0.08
    POSITIVE LOGITS
    /inc
    0.19
    aly
    0.16
    ally
    0.13
    /Error
    0.13
    ALLY
    0.13
    als
    0.13
    uate
    0.13
     prone
    0.12
     collisions
    0.11
    identally
    0.11
    Activations Density 0.054%

    No Known Activations