© 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. 812
    Prev
    Next
    INDEX
    Explanations

    say assassination

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

    No Comments

    Negative Logits
    畲
    -20.25
    (torch
    -18.88
    晋江
    -18.38
    .bucket
    -17.63
    亚马逊
    -17.13
    obao
    -17.00
    爪
    -16.75
    _bucket
    -16.63
    洱
    -16.63
    杵
    -16.38
    POSITIVE LOGITS
     Oswald
    27.88
    子弹
    25.88
    枪
    25.88
     shot
    24.50
     assassination
    24.38
     JFK
    24.38
     shoot
    24.13
     Kennedy
    24.00
     handgun
    23.50
     shooting
    23.13
    Activations Density 0.042%

    No Known Activations