© 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. 2214
    Prev
    Next
    INDEX
    Explanations

    say "communication"

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

    No Comments

    Negative Logits
    [dim
    -21.38
    (dim
    -20.50
    dim
    -19.00
    Dim
    -18.00
     dim
    -17.75
     mat
    -17.50
     hyp
    -17.25
     Dim
    -17.13
     mill
    -17.13
    曲
    -16.88
    POSITIVE LOGITS
    通讯
    48.25
     Comm
    39.00
    Comm
    35.75
     comm
    35.25
    (comm
    34.25
    comm
    33.75
    发
    33.50
     COMM
    30.63
    .comm
    29.38
     communications
    28.38
    Activations Density 0.049%

    No Known Activations