© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14674
    Prev
    Next
    INDEX
    Explanations

    say "extremist"

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

    No Comments

    Negative Logits
    会计师
    -18.88
     marking
    -17.88
    节
    -17.13
    節
    -16.38
    cba
    -15.88
    呱
    -15.44
     UIScrollView
    -15.00
    Phot
    -14.94
    aroo
    -14.94
    工业企业
    -14.88
    POSITIVE LOGITS
     الإرهاب
    17.13
    壕
    16.13
     tert
    15.06
    隍
    14.69
    	auth
    14.25
     separat
    14.25
     synthesis
    13.81
    骇
    13.81
     populist
    13.69
    -rad
    13.69
    Activations Density 0.151%

    No Known Activations