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

    Neuronpedia

    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. 15464
    Prev
    Next
    INDEX
    Explanations

    雅思

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

    No Comments

    Negative Logits
    /weather
    -21.88
    贫血
    -20.13
    Crime
    -17.75
    头疼
    -17.38
     criminals
    -17.25
    疼
    -17.13
    武汉市
    -17.13
    长大了
    -17.00
    番茄
    -17.00
    (weather
    -17.00
    POSITIVE LOGITS
    潞
    23.38
     Falk
    21.88
     Marl
    21.75
     interceptor
    21.75
    HOOK
    20.50
    翎
    19.50
    ICC
    19.25
    ivos
    19.13
    鹕
    18.63
    拦截
    18.38
    Activations Density 0.320%

    No Known Activations