© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    say "突"

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

    No Comments

    Negative Logits
     mods
    -15.94
     stats
    -15.63
    Mods
    -15.44
     admin
    -15.38
     meds
    -15.00
    Stats
    -14.75
    宗
    -14.69
     túi
    -14.31
    stats
    -14.06
    admin
    -14.00
    POSITIVE LOGITS
    mut
    55.75
     mut
    54.50
    Mut
    52.75
    (mut
    52.50
     Mut
    52.50
    突
    51.00
     MUT
    49.75
     mutation
    48.25
    互
    47.50
    _mut
    44.75
    Activations Density 0.035%

    No Known Activations