© 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. 16248
    Prev
    Next
    INDEX
    Explanations

    say "differences"

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

    No Comments

    Negative Logits
    contro
    -18.00
     depression
    -17.75
    麒
    -17.00
    黄埔
    -16.88
    红线
    -16.00
     suppression
    -16.00
     CONNECTION
    -16.00
    蹙
    -15.81
     Depression
    -15.56
     depressed
    -15.50
    POSITIVE LOGITS
    -register
    18.25
     register
    18.13
    差异
    17.50
    差异化
    17.38
    注册
    17.00
    差别
    16.75
    eneric
    16.63
    风格
    16.13
    .Register
    16.13
     Register
    16.13
    Activations Density 0.281%

    No Known Activations