© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16167
    Prev
    Next
    INDEX
    Explanations

    legal terms

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

    No Comments

    Negative Logits
     umbrella
    -14.75
    imeo
    -12.69
    探し
    -12.13
     Lesbian
    -11.44
    塬
    -11.31
     lesbian
    -11.06
     synopsis
    -11.06
    ipple
    -10.88
     terse
    -10.81
    Outlined
    -10.81
    POSITIVE LOGITS
    ADM
    24.25
    DJ
    21.25
    战
    21.13
    阿尔
    20.50
    ADS
    20.25
    MC
    19.88
     Guth
    19.88
    cis
    19.63
    OPS
    19.50
     ADS
    19.50
    Activations Density 0.628%

    No Known Activations