© 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. 16953
    Prev
    Next
    INDEX
    Explanations

    dangerous conditions warn

    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
     booty
    -0.12
     fleece
    -0.11
    bard
    -0.11
     Associ
    -0.10
     tentative
    -0.10
    zel
    -0.09
    pj
    -0.09
     plunder
    -0.09
     fle
    -0.09
    ardin
    -0.09
    POSITIVE LOGITS
     hazardous
    0.25
     dangerous
    0.25
     unsafe
    0.21
     Dangerous
    0.21
    unsafe
    0.18
     knives
    0.18
     hazards
    0.18
     Hazard
    0.17
     sharp
    0.17
    Danger
    0.17
    Activations Density 0.558%

    No Known Activations