© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2487
    Prev
    Next
    INDEX
    Explanations

    say "emergency"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    保
    -20.13
    范
    -18.63
     meth
    -17.88
     Meth
    -17.75
     retain
    -16.75
    rink
    -15.94
     retaining
    -15.94
     Ret
    -15.50
    Retention
    -15.25
     Sam
    -14.88
    POSITIVE LOGITS
     emergency
    46.00
    Emergency
    43.50
     Emergency
    43.50
    应急
    42.25
    emergency
    42.00
    	em
    39.00
    /em
    37.50
     em
    37.25
    (em
    36.50
     emergencies
    35.25
    Activations Density 0.097%

    No Known Activations