© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2474
    Prev
    Next
    INDEX
    Explanations

    say 指

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

    No Comments

    Negative Logits
    器官
    -16.63
    otti
    -16.13
    戗
    -15.69
    aise
    -15.38
    \\"
    -15.06
    .optimize
    -14.75
    imentary
    -14.75
    .conn
    -14.38
    IPP
    -14.31
    _reserve
    -14.31
    POSITIVE LOGITS
    指
    51.50
     ptr
    36.00
    ptr
    29.00
    (ptr
    29.00
    Ptr
    28.63
    	ptr
    28.00
    指的是
    27.75
     Pat
    26.88
     Ptr
    25.88
     refers
    25.75
    Activations Density 0.086%

    No Known Activations