© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15899
    Prev
    Next
    INDEX
    Explanations

    Pointe du

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

    No Comments

    Negative Logits
    抖
    -18.25
    SETS
    -16.88
     Carry
    -16.75
    跳舞
    -16.50
    張
    -16.50
    震荡
    -16.38
     carry
    -16.25
    spread
    -15.81
     evacuated
    -15.63
    几张
    -15.56
    POSITIVE LOGITS
    <footer
    19.75
    反腐
    18.13
     lesb
    17.13
    assin
    17.00
    SUP
    16.50
     pirate
    16.38
     pod
    16.13
     Templ
    16.13
     Palestin
    16.00
    reb
    16.00
    Activations Density 0.630%

    No Known Activations