© 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. 15122
    Prev
    Next
    INDEX
    Explanations

    person names

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

    No Comments

    Negative Logits
     Kin
    -18.63
     mun
    -16.75
    K
    -16.75
     Kenn
    -15.94
     Tr
    -15.75
    发出
    -15.75
    Tr
    -15.69
    kit
    -15.50
    KM
    -15.50
    kw
    -15.44
    POSITIVE LOGITS
    _di
    16.75
    ored
    16.38
     DI
    16.13
    眼镜
    15.75
    rupted
    15.38
    �
    15.38
     di
    15.00
     Berger
    14.25
    ooled
    14.19
    uzzle
    13.75
    Activations Density 0.454%

    No Known Activations