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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15669
    Prev
    Next
    INDEX
    Explanations

    say skill

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

    No Comments

    Negative Logits
    共振
    -17.50
     Bos
    -15.75
    DataSource
    -15.38
    违法
    -15.19
    _CALC
    -14.88
     Hose
    -14.44
    postData
    -14.31
     PRES
    -14.25
     watchdog
    -14.25
    DOCUMENT
    -14.25
    POSITIVE LOGITS
     skill
    47.50
     skills
    47.50
    技能
    47.00
    Skill
    44.00
     Skill
    44.00
    skill
    43.00
     Skills
    43.00
    .skills
    43.00
    _skill
    42.25
    (skill
    42.25
    Activations Density 0.382%

    No Known Activations