© 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. 1843
    Prev
    Next
    INDEX
    Explanations

    [watch] => [ful]

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

    No Comments

    Negative Logits
    _watch
    -25.25
    _WATCH
    -24.75
     Watches
    -22.38
     Watch
    -21.25
    watch
    -20.88
    -watch
    -20.63
     watch
    -19.75
    WATCH
    -19.50
    Watch
    -19.38
    _tv
    -18.63
    POSITIVE LOGITS
    材料
    21.63
     energy
    21.13
    能源
    21.00
     material
    19.38
     Material
    18.88
     Energy
    18.38
     energies
    18.13
    エネルギー
    17.88
    material
    17.63
    -energy
    17.38
    Activations Density 0.077%

    No Known Activations