© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    [思想] => [上]

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

    No Comments

    Negative Logits
    思想
    -24.75
    	ts
    -22.75
    (ts
    -22.25
    思想政治
    -21.75
    .ts
    -21.50
    的思想
    -21.50
     Ts
    -21.38
    Ts
    -21.25
    TS
    -21.13
    /ts
    -21.13
    POSITIVE LOGITS
    ilet
    15.88
    游
    15.50
     geometric
    15.06
     cart
    15.06
     gal
    14.94
    钙
    14.88
    摇滚
    14.69
    壶
    14.63
    骑
    13.94
    癌
    13.88
    Activations Density 0.175%

    No Known Activations