© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    say "pol" words

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

    No Comments

    Negative Logits
    乙方
    -18.25
     Mercy
    -15.81
     Tyson
    -15.69
    .conn
    -15.50
    =req
    -15.31
    师父
    -15.31
    甲方
    -14.88
    SRC
    -14.75
     Src
    -14.56
    :req
    -14.50
    POSITIVE LOGITS
     pol
    94.00
     Pol
    92.50
    Pol
    89.00
    pol
    85.50
    (pol
    79.00
    _pol
    78.00
    .pol
    71.00
    /pol
    70.50
    -pol
    70.00
     polynomial
    66.50
    Activations Density 0.155%

    No Known Activations