© 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. 1159
    Prev
    Next
    INDEX
    Explanations

    灼 => 热

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

    No Comments

    Negative Logits
     Wort
    -19.50
    acho
    -17.38
     Palo
    -17.13
    舌头
    -16.88
    马
    -16.75
    Lex
    -16.63
    ingo
    -16.63
    lexical
    -16.13
    威尼斯
    -16.13
    burg
    -15.94
    POSITIVE LOGITS
    电池
    18.13
    /aws
    17.25
    Technical
    17.00
    邾
    16.63
    fabs
    16.38
    (fabs
    16.13
    technical
    15.63
    媒体
    15.38
    音
    15.25
    xcf
    15.19
    Activations Density 0.360%

    No Known Activations