© 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. 4198
    Prev
    Next
    INDEX
    Explanations

    warning and protective responses

    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
    agus
    -0.09
    635
    -0.08
     blinded
    -0.08
     calmly
    -0.08
     confidently
    -0.08
    agar
    -0.08
    ogo
    -0.08
     resurrection
    -0.08
     ethos
    -0.08
     unle
    -0.08
    POSITIVE LOGITS
     warning
    0.23
     protective
    0.22
    protect
    0.21
     serves
    0.21
     warnings
    0.19
     warns
    0.19
     protects
    0.19
     serve
    0.19
     protect
    0.19
     protecting
    0.19
    Activations Density 0.408%

    No Known Activations