© 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. 47277
    Prev
    Next
    INDEX
    Explanations

    rescue and danger situation

    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
    chy
    -0.11
     anonymity
    -0.10
    abar
    -0.09
     disgr
    -0.09
    Anonymous
    -0.09
     Shak
    -0.09
    Empty
    -0.09
    igu
    -0.09
     flush
    -0.09
    overn
    -0.09
    POSITIVE LOGITS
     hostage
    0.22
     trapped
    0.21
     threatened
    0.21
     kidnapped
    0.21
     endangered
    0.20
     hostages
    0.18
     peril
    0.18
     resc
    0.18
     distress
    0.18
     Rescue
    0.18
    Activations Density 0.299%

    No Known Activations