© 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. 15307
    Prev
    Next
    INDEX
    Explanations

    say drugs

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

    No Comments

    Negative Logits
     Fuk
    -17.50
    -Token
    -16.13
     Shib
    -16.00
    折扣
    -16.00
    LAG
    -15.94
    aver
    -15.44
    ène
    -15.00
    .pivot
    -14.75
     chuck
    -14.69
    lag
    -14.25
    POSITIVE LOGITS
     legalized
    18.13
    ドラ
    18.00
    罂
    16.88
    毒品
    16.13
    害
    15.75
    合法
    15.69
    icontrol
    15.63
    危害
    15.31
    受害
    15.19
    禁毒
    15.06
    Activations Density 0.142%

    No Known Activations