© 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. 1027
    Prev
    Next
    INDEX
    Explanations

    protein

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

    No Comments

    Negative Logits
    それで
    -22.13
    pii
    -18.88
    eka
    -16.75
    {
↵
    -16.63
    あ
    -16.50
    ije
    -15.88
    assi
    -15.81
     rg
    -15.31
    pper
    -15.25
    itura
    -15.06
    POSITIVE LOGITS
     ​​
    15.88
    邛
    15.38
    就近
    15.38
     raz
    15.00
    plies
    15.00
    Expanded
    14.75
    irst
    14.25
     cad
    14.13
     lẽ
    14.00
    沉重
    13.94
    Activations Density 0.016%

    No Known Activations