© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    do not say skill

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

    No Comments

    Negative Logits
    技能
    -46.25
     skill
    -41.25
    Skill
    -40.75
     skills
    -40.50
     Skills
    -37.50
     Skill
    -37.00
    skills
    -36.25
    技能培训
    -35.00
    skill
    -34.75
    _skill
    -33.75
    POSITIVE LOGITS
    华盛顿
    17.25
    矩阵
    16.38
    /ge
    15.50
     Washington
    15.31
    /logger
    15.25
     logarith
    15.25
     geomet
    15.19
    ::$_
    15.19
     Hof
    15.06
     Log
    15.00
    Activations Density 0.127%

    No Known Activations