© 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. 116507
    Prev
    Next
    INDEX
    Explanations

    danger; dangers; dangerous

    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
    ŃIJ
    -0.10
     Genetics
    -0.09
     Mong
    -0.09
    ort
    -0.09
     Watts
    -0.09
    /MIT
    -0.09
     glorious
    -0.09
     mirac
    -0.09
    tml
    -0.09
     evacuated
    -0.08
    POSITIVE LOGITS
     dangerous
    0.35
     Dangerous
    0.27
     unpredictable
    0.27
     dangers
    0.26
    danger
    0.26
     danger
    0.25
     dangerously
    0.23
    Danger
    0.23
     unpredict
    0.22
    -danger
    0.22
    Activations Density 0.156%

    No Known Activations