© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16024
    Prev
    Next
    INDEX
    Explanations

    say "non‑ASCII characters"

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

    No Comments

    Negative Logits
    廊
    -19.25
    apper
    -18.63
    殿
    -17.38
    中心主任
    -17.25
     centro
    -16.75
    .diag
    -16.50
    enton
    -16.38
    .asm
    -16.25
    篮
    -16.25
    中枢
    -16.00
    POSITIVE LOGITS
    苓
    18.38
    难民
    17.63
     recoil
    17.38
     Mour
    16.88
     NOTIFY
    16.75
    /bind
    16.38
    mination
    16.25
    lift
    16.25
     resign
    16.13
     lif
    15.94
    Activations Density 0.642%

    No Known Activations