© 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. 14064
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
    生成
    -25.88
     generated
    -24.75
     generate
    -24.38
     generation
    -23.63
    Generated
    -23.38
     generating
    -23.13
     generates
    -22.75
    Generate
    -22.50
    generate
    -22.38
     Generates
    -22.00
    POSITIVE LOGITS
    支
    16.88
     profile
    15.13
    MessageType
    14.94
     branches
    14.94
     Matching
    14.81
    柴
    14.81
     profiles
    14.75
     dissolved
    14.63
     MessageType
    14.63
     matching
    14.31
    Activations Density 0.975%

    No Known Activations