© 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. 14641
    Prev
    Next
    INDEX
    Explanations

    any => 小

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

    No Comments

    Negative Logits
    vak
    -20.50
    urses
    -20.50
     NTN
    -20.38
    kul
    -19.63
    publish
    -19.50
    Certificates
    -19.38
    註
    -19.25
    滘
    -19.00
    cka
    -19.00
    HCI
    -19.00
    POSITIVE LOGITS
    _t
    15.31
     t
    14.44
    S
    14.25
     tam
    14.06
    3
    13.75
    中小
    13.31
    小
    13.06
    _s
    13.00
    死
    12.94
     sh
    12.88
    Activations Density 0.028%

    No Known Activations