© 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. 16148
    Prev
    Next
    INDEX
    Explanations

    [学家] => [学家]

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

    No Comments

    Negative Logits
    脱
    -21.50
    	de
    -19.13
    -de
    -19.00
    脫
    -18.88
    _de
    -18.63
    _De
    -18.13
     Deserialize
    -18.13
     DE
    -18.13
     De
    -18.00
    /de
    -18.00
    POSITIVE LOGITS
    PAR
    18.50
    Cl
    18.50
    par
    18.00
    Par
    17.88
     par
    16.63
    CLU
    16.63
    -par
    16.50
    _Cl
    16.50
    (Cl
    16.50
     birds
    16.50
    Activations Density 1.283%

    No Known Activations