© 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. 16361
    Prev
    Next
    INDEX
    Explanations

    acknowledgment

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

    No Comments

    Negative Logits
     Crash
    -17.88
    桁
    -17.75
    technology
    -17.50
    olla
    -17.00
     crashing
    -16.88
    颠覆
    -16.88
     Интернет
    -16.88
     rocker
    -16.75
    混沌
    -16.75
    agma
    -16.50
    POSITIVE LOGITS
    CSR
    17.50
    avor
    16.25
    urban
    15.38
     devout
    14.88
    ใ
    14.75
    优惠
    14.75
    덕
    14.25
    umin
    14.19
     urban
    14.06
     Ain
    14.00
    Activations Density 0.280%

    No Known Activations