© 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. 15116
    Prev
    Next
    INDEX
    Explanations

    [Sir] => [Thomas]

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

    No Comments

    Negative Logits
    akin
    -20.00
    王者
    -19.13
     setC
    -18.25
    oric
    -18.00
    文科
    -17.75
     bidi
    -17.63
    登入
    -17.38
    贲
    -17.25
     Bret
    -17.13
    enci
    -17.00
    POSITIVE LOGITS
     deflate
    15.44
    薯
    14.81
    agh
    14.56
     Hugh
    14.19
    =sub
    14.06
    ща
    13.88
    sub
    13.56
     sub
    13.56
    subs
    13.56
    oll
    13.06
    Activations Density 0.878%

    No Known Activations