© 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. 1395
    Prev
    Next
    INDEX
    Explanations

    non‑yellow colors

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

    No Comments

    Negative Logits
    黃
    -36.50
    黄色
    -34.50
    黄
    -34.50
     yellow
    -33.00
    黄金
    -30.00
     Yellow
    -29.63
    yellow
    -28.50
    YELLOW
    -28.13
    黄河
    -27.75
    Yellow
    -27.25
    POSITIVE LOGITS
    ran
    16.13
    /Card
    15.50
     construct
    15.19
    矢
    14.88
    construct
    14.88
     Vect
    14.56
    vector
    14.50
    orca
    14.06
     Beast
    13.94
     constructive
    13.75
    Activations Density 0.096%

    No Known Activations