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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 174
    Prev
    Next
    INDEX
    Explanations

    Russian tsars

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

    No Comments

    Negative Logits
     Tucson
    -24.00
     Somali
    -24.00
     Nairobi
    -22.50
    十堰
    -22.13
     Asheville
    -21.63
     AFC
    -21.38
    贵阳
    -21.25
     UB
    -21.25
    梅州
    -20.88
    杭
    -20.75
    POSITIVE LOGITS
    (ts
    20.75
     ts
    19.63
    (Token
    18.13
     louis
    17.88
     Alexandre
    17.63
    (ds
    17.38
    (es
    17.25
    /ts
    17.25
     ds
    17.13
    ippi
    17.13
    Activations Density 0.060%

    No Known Activations