© 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. 2728
    Prev
    Next
    INDEX
    Explanations

    say "rescue"

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

    No Comments

    Negative Logits
     config
    -17.25
     Iter
    -17.25
    .config
    -17.00
     membrane
    -16.88
    膜
    -16.75
    -dat
    -16.75
    =config
    -16.63
    手感
    -16.50
    品
    -16.50
    modal
    -16.50
    POSITIVE LOGITS
    救援
    47.50
     rescue
    45.25
     Rescue
    43.00
     rescued
    36.75
    救
    36.00
     resc
    32.75
    被困
    26.00
    救人
    25.13
    RES
    23.13
     RES
    22.88
    Activations Density 0.084%

    No Known Activations