© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1071
    Prev
    Next
    INDEX
    Explanations

    say "pol"

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

    No Comments

    Negative Logits
    (Sql
    -19.13
    SqlServer
    -17.88
    SqlParameter
    -16.88
     SqlParameter
    -15.31
    蹴
    -14.94
     SqlConnection
    -14.50
    PUT
    -14.38
    _sql
    -14.19
     SqlDataReader
    -14.06
    西北
    -14.00
    POSITIVE LOGITS
     pol
    25.63
    _pol
    23.75
    pol
    23.75
     Gold
    23.13
     gold
    22.50
     Pol
    22.50
    Gold
    22.00
    Pol
    21.63
    (pol
    21.38
    POL
    20.13
    Activations Density 0.260%

    No Known Activations