© 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. 2158
    Prev
    Next
    INDEX
    Explanations

    say superscript numbers

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

    No Comments

    Negative Logits
    发
    -16.50
    templ
    -15.75
    (operation
    -15.44
    .operation
    -15.38
    薄膜
    -15.06
     Relief
    -14.94
    PT
    -14.75
     Emm
    -14.56
    _operation
    -14.50
     Films
    -14.44
    POSITIVE LOGITS
    ³
    58.25
    ¹
    55.00
    ²
    54.75
    �
    54.75
     �
    48.00
    ⁻
    41.25
    壹
    40.00
    �
    38.50
    乙方
    36.75
    叁
    36.50
    Activations Density 0.071%

    No Known Activations