© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 166
    Prev
    Next
    INDEX
    Explanations

    say three-letter caps

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

    No Comments

    Negative Logits
     Rs
    -24.50
    Rs
    -23.00
     Js
    -22.00
    Ds
    -21.00
    Js
    -20.75
     Bs
    -20.50
    (Cs
    -20.13
    Cs
    -20.00
     LS
    -19.38
    萧
    -19.13
    POSITIVE LOGITS
     MAS
    35.00
     SAM
    33.75
    CAM
    33.00
     CAS
    32.50
    MAS
    32.50
     CAM
    32.50
     MAR
    31.50
     CAB
    31.38
     DAM
    30.38
     MAC
    30.38
    Activations Density 0.434%

    No Known Activations