© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15310
    Prev
    Next
    INDEX
    Explanations

    hex addresses

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

    No Comments

    Negative Logits
    討
    -21.38
    gov
    -20.50
    Demon
    -18.63
    getBlock
    -17.75
     Advocate
    -17.50
    codes
    -17.25
    een
    -17.00
    跑了
    -16.63
    入侵
    -16.63
    xec
    -16.63
    POSITIVE LOGITS
    lz
    14.50
    睫
    13.25
     opts
    13.00
    莒
    12.88
    和发展
    12.56
     TSRMLS
    12.50
    娄
    12.19
    {l
    12.19
    兰花
    12.19
    ʊ
    12.00
    Activations Density 0.027%

    No Known Activations