© 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. 16204
    Prev
    Next
    INDEX
    Explanations

    fruits and nuts

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

    No Comments

    Negative Logits
    AGE
    -18.25
    AGES
    -18.00
    AGER
    -17.13
    _quality
    -17.00
    祺
    -16.63
    Administrator
    -16.50
    �
    -16.13
    ướng
    -16.13
    Diagnostic
    -16.13
    运动会
    -16.00
    POSITIVE LOGITS
     sticky
    15.88
    稼
    14.75
     pumps
    14.75
     seeds
    13.31
     sticks
    13.19
    .mul
    13.06
    epam
    13.00
     moll
    12.94
    蒴
    12.88
    핀
    12.56
    Activations Density 0.187%

    No Known Activations