© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16123
    Prev
    Next
    INDEX
    Explanations

    subword pieces

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

    No Comments

    Negative Logits
    万户
    -20.88
     Devil
    -20.25
     buffet
    -18.25
    额头
    -18.13
    仙
    -18.13
    髻
    -18.00
     devil
    -17.50
    帽
    -17.38
     magistrate
    -16.88
    箕
    -16.63
    POSITIVE LOGITS
    bre
    18.38
     bre
    17.25
    elier
    16.75
     Bre
    16.75
    PLEX
    16.38
    培
    16.00
     recur
    16.00
    imity
    15.94
    密
    15.88
    allel
    15.75
    Activations Density 0.581%

    No Known Activations