© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15852
    Prev
    Next
    INDEX
    Explanations

    say non-Latin characters

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

    No Comments

    Negative Logits
     EL
    -31.25
    EL
    -30.63
    wl
    -30.00
     wl
    -29.13
    (dl
    -28.75
     RL
    -28.25
    ol
    -28.00
    อล
    -27.88
     DL
    -27.88
     AL
    -27.88
    POSITIVE LOGITS
    翠
    16.63
    gren
    16.00
    ceptive
    15.81
    桠
    15.75
    彩虹
    15.75
     Townsend
    15.69
    鹬
    15.63
    闰
    15.44
    esseract
    15.38
    姥
    15.38
    Activations Density 0.007%

    No Known Activations