© 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. 2385
    Prev
    Next
    INDEX
    Explanations

    say profit

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

    No Comments

    Negative Logits
    乙方
    -20.25
     Tyson
    -19.50
     moderators
    -18.75
     moderator
    -17.25
    .eq
    -17.00
    甲方
    -16.88
     Cyril
    -16.88
     Moderator
    -16.75
     MOD
    -16.75
     Ty
    -16.75
    POSITIVE LOGITS
    利
    77.00
     profit
    38.50
    利润
    37.25
    Profit
    33.50
     exploited
    32.75
     lợi
    32.50
     Profit
    32.50
     lib
    32.25
    profit
    31.63
     exploit
    31.38
    Activations Density 0.076%

    No Known Activations