© 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. 14847
    Prev
    Next
    INDEX
    Explanations

    digits

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

    No Comments

    Negative Logits
    unnel
    -19.63
    utton
    -19.38
    悚
    -19.25
     Conte
    -17.88
    enne
    -17.63
    ullo
    -17.38
     Soldier
    -17.13
    坑
    -16.88
    洞
    -16.88
     Moff
    -16.63
    POSITIVE LOGITS
    riz
    17.88
    アジ
    17.50
    ahr
    16.88
    adx
    16.88
     florida
    16.63
     herpes
    16.50
    僖
    16.50
    Trivia
    16.38
    asz
    16.13
     Philipp
    16.00
    Activations Density 0.050%

    No Known Activations