© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    say 条

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

    No Comments

    Negative Logits
    Vec
    -20.50
    vec
    -19.63
     consul
    -19.50
     Vec
    -18.75
    .ctx
    -18.38
     vec
    -17.38
     Mut
    -17.38
    Sim
    -17.13
    curve
    -17.00
    drs
    -16.50
    POSITIVE LOGITS
    条
    29.63
    條
    20.38
    [param
    17.75
    =obj
    17.50
    	param
    16.13
    条规定
    15.88
     param
    15.81
    范
    15.44
     meg
    15.44
     territory
    15.44
    Activations Density 0.037%

    No Known Activations