© 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. 16002
    Prev
    Next
    INDEX
    Explanations

    say "games"

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

    No Comments

    Negative Logits
     chronic
    -16.50
     lethal
    -16.38
     histor
    -15.81
    伉
    -15.38
    dense
    -15.38
     indexed
    -15.31
    SUP
    -15.25
     ayr
    -15.25
    ahir
    -15.06
    .inject
    -15.00
    POSITIVE LOGITS
    小朋友
    20.25
    小游戏
    20.00
    泡泡
    19.88
    游戏
    19.50
    魔术
    19.25
    活动
    18.88
    魔法
    18.13
    绿色
    17.75
     magician
    17.75
    的游戏
    17.63
    Activations Density 0.244%

    No Known Activations