© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2207
    Prev
    Next
    INDEX
    Explanations

    say "backticks"

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

    No Comments

    Negative Logits
    TER
    -23.50
    ter
    -20.88
     ter
    -20.50
     config
    -20.00
     Territory
    -19.38
     configs
    -18.38
     TER
    -17.88
    _ter
    -17.25
    Ter
    -17.13
    ERT
    -16.38
    POSITIVE LOGITS
    乙方
    29.63
    vec
    27.25
    甲方
    26.50
    (vec
    26.13
     Vec
    25.75
    (Vec
    25.63
     vec
    24.63
     Meth
    24.00
    	vec
    23.63
    丙
    23.38
    Activations Density 0.090%

    No Known Activations