© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15997
    Prev
    Next
    INDEX
    Explanations

    say "non‑ASCII"

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

    No Comments

    Negative Logits
     Ryder
    -25.75
    蜻
    -23.88
     Nolan
    -23.38
     PARK
    -23.13
     polo
    -23.00
     bubble
    -22.75
     Cree
    -22.25
     bubbles
    -22.13
    bubble
    -22.00
     Wolves
    -21.88
    POSITIVE LOGITS
    仙境
    24.50
    晋
    24.13
    (hWnd
    22.25
     lizard
    21.88
    瑶
    21.75
     Welch
    21.63
     Scotch
    21.38
    hci
    20.50
    pcl
    20.13
     Midi
    20.00
    Activations Density 6.690%

    No Known Activations