© 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. 1363
    Prev
    Next
    INDEX
    Explanations

    say telephone

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

    No Comments

    Negative Logits
    构造
    -24.25
     construct
    -23.50
     �
    -22.75
     constructive
    -22.50
    钢结构
    -21.38
    构建
    -21.25
    架构
    -21.25
     Construct
    -20.38
    construct
    -19.50
    .construct
    -19.13
    POSITIVE LOGITS
     telephone
    20.00
     телефон
    19.63
     telefon
    18.75
    电话
    18.50
    phones
    17.88
     телеф
    17.75
     phone
    17.63
     Telephone
    17.00
    Phone
    16.88
     telefone
    16.75
    Activations Density 0.138%

    No Known Activations