© 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. 2522
    Prev
    Next
    INDEX
    Explanations

    say pot words

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

    No Comments

    Negative Logits
    甲方
    -19.88
    乙方
    -18.50
    代
    -17.75
     DEL
    -17.00
    二代
    -16.63
    EMPL
    -16.50
    DEL
    -16.25
    .arr
    -15.63
    	del
    -15.50
    erializer
    -15.38
    POSITIVE LOGITS
     pot
    85.00
     Pot
    82.00
    Pot
    81.50
    pot
    78.50
    _pot
    63.25
     POT
    60.75
     pots
    55.25
     potentials
    46.50
     potential
    40.25
     пот
    38.00
    Activations Density 0.125%

    No Known Activations