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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15968
    Prev
    Next
    INDEX
    Explanations

    say "rights"

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

    No Comments

    Negative Logits
    女王
    -17.38
    oser
    -16.50
     Queen
    -16.25
    省教育
    -16.25
    NES
    -15.44
    罄
    -15.44
    olley
    -15.13
     chocol
    -15.00
    verted
    -14.88
     Osc
    -14.88
    POSITIVE LOGITS
    ajs
    20.25
    权
    18.50
    _rights
    17.88
     Dien
    17.63
     Rights
    17.50
    服从
    17.38
    -rights
    17.25
     rights
    17.00
    rights
    16.88
    Rights
    16.50
    Activations Density 0.020%

    No Known Activations