© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1153
    Prev
    Next
    INDEX
    Explanations

    do not say blood

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

    No Comments

    Negative Logits
    血液
    -35.25
     Blood
    -29.13
    血
    -28.75
     blood
    -28.63
    Blood
    -28.38
    气血
    -27.75
    鲜血
    -27.75
    blood
    -27.75
     máu
    -27.63
     крови
    -27.25
    POSITIVE LOGITS
    法师
    18.63
    创新
    17.50
     polynomial
    16.00
     innovations
    15.94
     Polynomial
    15.25
     innovation
    15.06
    之城
    15.06
    ψ
    14.94
    Ψ
    14.25
     Fischer
    14.19
    Activations Density 0.118%

    No Known Activations