© 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. 816
    Prev
    Next
    INDEX
    Explanations

    Hen

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

    No Comments

    Negative Logits
    碛
    -19.13
     Blizzard
    -18.63
     Mozart
    -18.25
    KP
    -17.25
    ಶ
    -16.75
    张家界
    -16.63
    礁
    -16.13
     OD
    -16.13
    羊毛
    -15.94
    桂林
    -15.81
    POSITIVE LOGITS
     Hen
    37.50
    Hen
    35.75
    HEN
    31.75
     hen
    28.13
     Henrik
    26.63
    hen
    25.38
    苯
    23.88
     Henri
    23.25
     Beng
    22.38
     Jen
    21.63
    Activations Density 0.151%

    No Known Activations