© 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. 15880
    Prev
    Next
    INDEX
    Explanations

    den

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

    No Comments

    Negative Logits
    炕
    -17.63
    offee
    -17.25
    yth
    -16.75
    KIT
    -16.50
    Cong
    -16.13
     Cong
    -16.00
    xEF
    -15.88
    QQ
    -15.69
    栗
    -15.69
    reo
    -15.63
    POSITIVE LOGITS
    zion
    16.50
    zn
    16.13
    phans
    14.69
     Sandra
    14.44
    蚩
    14.38
     obr
    14.25
     masculinity
    14.25
    .den
    14.19
     darkness
    14.13
    柬埔寨
    14.13
    Activations Density 0.006%

    No Known Activations