© 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. 15408
    Prev
    Next
    INDEX
    Explanations

    say "th"

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

    No Comments

    Negative Logits
    榉
    -16.38
     Giul
    -16.25
     Ku
    -15.25
     gó
    -15.13
    迁
    -15.13
    枧
    -15.13
    龙门
    -15.00
    经开
    -15.00
    菅
    -15.00
    struk
    -14.94
    POSITIVE LOGITS
    -th
    64.50
    Th
    63.25
    -Th
    58.00
     Th
    57.75
    (th
    57.75
    	th
    56.50
     TH
    55.75
    TH
    54.75
    th
    54.25
    _th
    53.75
    Activations Density 5.305%

    No Known Activations