© 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. 16178
    Prev
    Next
    INDEX
    Explanations

    efficient

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

    No Comments

    Negative Logits
    pta
    -16.88
    stry
    -16.13
    滹
    -15.94
    PARSE
    -15.50
    部副部长
    -15.38
    igar
    -15.38
    xpath
    -14.88
    (par
    -14.81
    appa
    -14.81
     Chapman
    -14.69
    POSITIVE LOGITS
    lec
    16.88
    urf
    16.75
    uf
    16.50
    oce
    16.38
     Ale
    16.25
    抗生素
    16.25
    rif
    16.00
    oc
    15.19
     lettuce
    15.19
    ockets
    15.13
    Activations Density 0.006%

    No Known Activations