© 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. 15937
    Prev
    Next
    INDEX
    Explanations

    say Chinese characters

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

    No Comments

    Negative Logits
     JJ
    -49.00
    JA
    -46.25
    JO
    -45.50
    jet
    -45.50
    -j
    -45.50
    -J
    -45.50
    ja
    -44.75
    JE
    -44.50
    JP
    -43.75
    JC
    -43.75
    POSITIVE LOGITS
    腓
    16.88
    堃
    15.31
    焘
    14.75
    庹
    14.13
     penn
    14.00
    撸
    13.81
    薇
    13.50
    滏
    13.44
    殇
    13.38
    SCO
    13.25
    Activations Density 3.462%

    No Known Activations