© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113979
    Prev
    Next
    INDEX
    Explanations

    caught doing something

    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
     langs
    -0.11
     Dew
    -0.10
    ood
    -0.10
     Euro
    -0.10
     Rowe
    -0.10
     ominous
    -0.10
     ingl
    -0.10
     hitch
    -0.09
    ForegroundColor
    -0.09
    NEWS
    -0.09
    POSITIVE LOGITS
     unaware
    0.11
     off
    0.09
     before
    0.09
     mid
    0.09
     net
    0.08
    beam
    0.08
     eye
    0.08
     vulnerable
    0.08
     drains
    0.08
     draining
    0.08
    Activations Density 0.026%

    No Known Activations