© 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. 949
    Prev
    Next
    INDEX
    Explanations

    say "ends with T"

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

    No Comments

    Negative Logits
    芜湖
    -15.00
    合肥
    -15.00
    mong
    -14.25
    淮
    -13.44
    崀
    -13.31
    isma
    -13.13
    蚌埠
    -13.13
    簪
    -13.00
    鄱
    -13.00
    umbai
    -12.94
    POSITIVE LOGITS
     PT
    73.50
     CT
    72.00
     FT
    69.00
     DT
    67.00
     MT
    67.00
     HT
    66.00
     RT
    65.50
    CT
    64.50
     GT
    63.50
     VT
    62.75
    Activations Density 1.098%

    No Known Activations