© 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. 2528
    Prev
    Next
    INDEX
    Explanations

    say 潜

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

    No Comments

    Negative Logits
     Melissa
    -18.13
    Fil
    -17.75
    代
    -17.38
    世代
    -16.63
    Matt
    -16.50
    empor
    -16.38
     strips
    -16.38
     fil
    -16.25
    rets
    -16.25
    _ros
    -15.94
    POSITIVE LOGITS
    潜
    44.75
     pot
    34.75
    潛
    33.50
     Pot
    32.75
    Pot
    31.50
    pot
    31.25
     POT
    28.25
    _pot
    26.75
     mer
    22.13
     potentials
    22.13
    Activations Density 0.057%

    No Known Activations