© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14013
    Prev
    Next
    INDEX
    Explanations

    say contributions

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

    No Comments

    Negative Logits
    练习
    -17.38
    申诉
    -16.63
    襦
    -15.81
     Curso
    -15.50
    慌
    -15.38
     �
    -15.13
    練
    -15.13
    教练
    -15.06
    复习
    -15.06
    irate
    -14.94
    POSITIVE LOGITS
    贡献
    30.63
     contributions
    30.13
     contribution
    29.50
    里程碑
    26.63
     Contributions
    24.88
     Contribution
    24.25
    contrib
    23.13
     milestones
    23.13
     contributors
    22.88
     milestone
    22.88
    Activations Density 0.656%

    No Known Activations