© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 307
    Prev
    Next
    INDEX
    Explanations

    prevention, safety, and protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     productive
    -0.10
     Liberation
    -0.09
    ascript
    -0.09
     dissatisfaction
    -0.09
     impatient
    -0.09
     economists
    -0.09
     Taxes
    -0.09
     Starter
    -0.09
     Satisfaction
    -0.09
    peg
    -0.08
    POSITIVE LOGITS
     safety
    0.33
     precaution
    0.30
     precautions
    0.30
     protection
    0.27
     risk
    0.26
     safeguard
    0.26
     safer
    0.25
     Safety
    0.25
     protective
    0.25
     protect
    0.25
    Activations Density 3.057%

    No Known Activations