© 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. 15909
    Prev
    Next
    INDEX
    Explanations

    say syntactic tags

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

    No Comments

    Negative Logits
    浣
    -16.13
    笤
    -15.69
     MCS
    -15.31
    米兰
    -15.13
     Glacier
    -15.06
    炬
    -15.00
    ktor
    -15.00
    strom
    -14.81
    炀
    -14.81
    冼
    -14.75
    POSITIVE LOGITS
    (gp
    38.75
    (dp
    38.50
     DP
    38.00
    (rp
    37.75
    (vp
    37.50
    RP
    37.25
     GP
    37.25
     RP
    37.00
    gp
    36.50
    qp
    36.50
    Activations Density 6.759%

    No Known Activations