© 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. 15949
    Prev
    Next
    INDEX
    Explanations

    legal disclaimer

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

    No Comments

    Negative Logits
    蛀
    -18.00
     burn
    -17.00
    挂
    -16.00
    虹
    -16.00
    撞击
    -15.69
    卫浴
    -15.38
    -inc
    -15.25
    镀
    -15.19
     coating
    -15.13
    bow
    -15.00
    POSITIVE LOGITS
    iske
    19.63
    sk
    19.50
     Hundred
    18.38
    énom
    18.25
    岛
    17.75
     Prairie
    17.50
     sk
    17.13
    九州
    17.00
    raising
    17.00
    _sk
    16.38
    Activations Density 0.535%

    No Known Activations