© 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. 14224
    Prev
    Next
    INDEX
    Explanations

    non‑Latin script

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

    No Comments

    Negative Logits
     training
    -20.75
    training
    -19.38
    训练
    -19.25
    机制
    -18.38
    Training
    -18.13
    培训
    -17.63
     Training
    -17.63
    running
    -17.38
    -training
    -17.38
     running
    -17.25
    POSITIVE LOGITS
    发
    17.13
     comm
    15.81
    验证
    15.63
     inter
    14.94
     method
    14.94
    삽
    14.56
    zia
    14.44
     Verification
    14.38
    发送
    14.19
    (comm
    14.19
    Activations Density 1.145%

    No Known Activations