© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15639
    Prev
    Next
    INDEX
    Explanations

    say "leak"

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

    No Comments

    Negative Logits
    ucker
    -16.63
     orb
    -16.38
    联社
    -15.56
    PELL
    -15.38
    caps
    -15.13
     Zub
    -15.13
     ell
    -14.38
     ib
    -14.31
    宇
    -14.25
     puck
    -14.19
    POSITIVE LOGITS
     leaks
    18.38
     infiltration
    18.25
     plagiarism
    17.75
    leasing
    17.00
     Leak
    16.50
     invasion
    16.38
     Planning
    16.25
    读懂
    16.25
     leaking
    16.25
    align
    16.00
    Activations Density 0.529%

    No Known Activations