© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16233
    Prev
    Next
    INDEX
    Explanations

    say "tying"

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

    No Comments

    Negative Logits
     ASIC
    -17.00
    水质
    -17.00
    配音
    -16.38
    谤
    -16.13
    碑
    -16.13
    碧桂园
    -15.94
    楯
    -15.63
    羞
    -15.50
     Plate
    -15.19
    评委
    -15.19
    POSITIVE LOGITS
    绑
    28.63
    绳
    26.50
     binding
    25.88
     ties
    25.63
     tying
    25.38
    Bindings
    25.25
    拴
    25.00
     string
    24.75
     tied
    24.50
     tie
    24.50
    Activations Density 0.345%

    No Known Activations