© 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. 15967
    Prev
    Next
    INDEX
    Explanations

    [any] => N

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

    No Comments

    Negative Logits
    CHR
    -19.13
    摄影
    -18.75
    票
    -18.50
    (photo
    -18.13
     Photography
    -18.13
     фото
    -17.63
     photo
    -17.50
     photography
    -17.13
    照片
    -17.00
     Photo
    -16.75
    POSITIVE LOGITS
    狒
    20.50
    嵬
    19.75
     Kurt
    19.25
    傈
    19.00
     Bulld
    18.88
     Jarvis
    18.75
    碶
    18.50
     vestib
    18.25
    蛟
    18.13
    izu
    17.88
    Activations Density 0.254%

    No Known Activations