© 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. 15886
    Prev
    Next
    INDEX
    Explanations

    say target

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

    No Comments

    Negative Logits
    [mask
    -18.38
    	mask
    -17.75
    roke
    -17.50
    clare
    -17.50
    徑
    -16.88
    ляр
    -15.81
    TEM
    -15.75
    avour
    -15.69
     pard
    -15.56
    ку
    -15.44
    POSITIVE LOGITS
     targets
    22.25
     target
    22.00
    靶
    21.13
    .targets
    21.13
    target
    19.88
    targets
    19.38
    Targets
    19.00
    _targets
    18.38
     Targets
    18.13
    目标
    18.13
    Activations Density 0.240%

    No Known Activations