© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15363
    Prev
    Next
    INDEX
    Explanations

    say "hit" words

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

    No Comments

    Negative Logits
     Shib
    -24.63
     Shir
    -23.00
    希腊
    -21.75
    政协
    -20.63
     Hermione
    -20.63
    _PY
    -20.38
     svn
    -20.13
    游艇
    -20.13
    工商联
    -20.13
    仙
    -20.00
    POSITIVE LOGITS
    捶
    28.00
    撞击
    23.88
     Bang
    23.38
     Glock
    22.88
    槌
    22.63
    击
    22.25
     Hammer
    22.00
    爆
    21.88
    撞
    21.63
     hammer
    21.50
    Activations Density 8.363%

    No Known Activations