© 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. 2193
    Prev
    Next
    INDEX
    Explanations

    say "potassium"

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

    No Comments

    Negative Logits
    曲
    -19.13
     Resolve
    -17.38
    usic
    -16.50
    specs
    -15.38
    鹿
    -14.94
    悯
    -14.88
    Resolve
    -14.75
    (cur
    -14.75
    特
    -14.69
     Env
    -14.56
    POSITIVE LOGITS
     Pot
    50.00
    Pot
    50.00
     potassium
    46.75
    pot
    43.00
    钾
    39.00
    _pot
    38.75
     pot
    38.50
     POT
    37.75
     potentials
    26.00
    Potential
    24.25
    Activations Density 0.051%

    No Known Activations