© 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. 1666
    Prev
    Next
    INDEX
    Explanations

    say "ax" words

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

    No Comments

    Negative Logits
    诗词
    -18.38
    emic
    -17.13
    航海
    -16.25
    芯片
    -16.13
    VED
    -15.44
    /GPL
    -15.19
     ship
    -15.19
     metallic
    -15.00
     Eddie
    -14.94
    舱
    -14.88
    POSITIVE LOGITS
    ax
    19.88
     Ax
    19.13
    ImageButton
    19.00
    图像
    18.38
    木
    18.38
    axon
    18.13
    AX
    18.13
     AX
    18.00
    Images
    17.63
    _tok
    17.38
    Activations Density 0.241%

    No Known Activations