© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15014
    Prev
    Next
    INDEX
    Explanations

    say "sh" words

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

    No Comments

    Negative Logits
    李先生
    -19.00
     Piper
    -18.63
    rics
    -18.13
    PTY
    -17.75
    平
    -17.13
    pData
    -16.63
    pty
    -16.50
    (pf
    -16.13
    otation
    -15.94
     diffusion
    -15.94
    POSITIVE LOGITS
     shake
    20.88
    shake
    20.63
    usk
    20.25
    -Sh
    19.75
    Sh
    19.13
    -sh
    18.63
     shard
    18.38
     Shake
    18.13
    Sk
    18.13
    sh
    17.75
    Activations Density 0.870%

    No Known Activations