© 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. 15962
    Prev
    Next
    INDEX
    Explanations

    relationship

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

    No Comments

    Negative Logits
    恐慌
    -16.13
    妒
    -16.00
    PGA
    -15.94
    ลาด
    -15.31
    pga
    -15.25
    在家里
    -15.25
     HOME
    -15.19
     Guidance
    -15.13
    安置
    -15.00
     home
    -14.69
    POSITIVE LOGITS
    蜜
    19.13
    修
    18.50
    脩
    18.25
    bond
    16.88
    持有人
    16.50
    处理
    16.38
    Clickable
    16.13
    няти
    15.94
    cord
    15.94
     bond
    15.94
    Activations Density 0.205%

    No Known Activations