© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15235
    Prev
    Next
    INDEX
    Explanations

    的

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

    No Comments

    Negative Logits
    脲
    -18.50
    edm
    -17.38
    辙
    -17.25
    eve
    -17.13
    维权
    -17.00
     Klo
    -17.00
    ót
    -16.88
    氨基酸
    -16.75
    umi
    -16.50
    馍
    -16.50
    POSITIVE LOGITS
    var
    14.81
    go
    14.00
    层层
    13.81
    сс
    13.31
     entry
    12.81
    rect
    12.50
    script
    12.06
    ceptor
    12.06
    (s
    11.88
    有
    11.88
    Activations Density 0.144%

    No Known Activations