© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1490
    Prev
    Next
    INDEX
    Explanations

    Chinese herbs

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

    No Comments

    Negative Logits
     Ether
    -18.25
     cig
    -18.13
    Ether
    -17.75
    arb
    -17.63
     ether
    -17.13
     Hammer
    -16.38
     Mick
    -16.38
     pencil
    -16.25
     arp
    -16.00
    ether
    -15.88
    POSITIVE LOGITS
    源头
    16.88
    ilder
    15.56
    穿衣
    15.31
    >Login
    14.81
    ioni
    14.69
    动物
    14.63
    登入
    14.56
    登陆
    14.38
    矩阵
    14.31
     showAlert
    14.19
    Activations Density 0.056%

    No Known Activations