© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    say "variety"

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

    No Comments

    Negative Logits
     avi
    -15.50
    vy
    -15.06
    äng
    -14.56
    ilities
    -14.38
    phil
    -14.31
     pilot
    -14.31
    测量
    -14.13
    壕
    -13.75
     mic
    -13.69
    measurement
    -13.50
    POSITIVE LOGITS
    品种
    52.25
    品
    49.50
     varieties
    34.25
     variety
    28.63
     Variety
    27.63
    品类
    26.25
     var
    25.50
    품
    25.50
    Vari
    25.00
    新品
    25.00
    Activations Density 0.041%

    No Known Activations