© 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. 15964
    Prev
    Next
    INDEX
    Explanations

    say expulsion

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

    No Comments

    Negative Logits
    ZY
    -17.38
    brid
    -17.00
     Zag
    -16.75
    bra
    -16.63
    inz
    -16.50
    养猪
    -16.25
    钢板
    -16.25
    zen
    -16.13
    zy
    -16.13
    -login
    -16.00
    POSITIVE LOGITS
    排出
    37.75
    排放
    36.50
    出口
    33.25
    排
    33.00
     expelled
    31.38
     discharge
    30.50
     emit
    29.63
     emission
    29.25
     emitted
    29.13
    排气
    28.75
    Activations Density 0.328%

    No Known Activations