© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14307
    Prev
    Next
    INDEX
    Explanations

    [self] => [self]

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

    No Comments

    Negative Logits
     calend
    -16.63
     Chun
    -16.50
    同城
    -16.13
    _CACHE
    -15.94
    LOCAL
    -15.88
    当地政府
    -15.75
     local
    -15.69
    转运
    -15.56
     unsubscribe
    -15.44
    PIPE
    -15.44
    POSITIVE LOGITS
    自卑
    22.50
    自信
    22.13
    自我
    22.00
     Confidence
    21.88
     identities
    21.75
     validation
    21.38
    自豪
    21.38
    -self
    21.13
     Identity
    21.13
     identity
    21.00
    Activations Density 0.454%

    No Known Activations