© 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. 15615
    Prev
    Next
    INDEX
    Explanations

    kin => Simpkin

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

    No Comments

    Negative Logits
     plat
    -22.25
     Uni
    -21.13
     SEAL
    -20.88
     UCS
    -20.25
    opi
    -17.88
     Platt
    -17.63
     Geli
    -17.25
     Marl
    -17.13
     Monterey
    -16.50
    平台
    -16.38
    POSITIVE LOGITS
    仙女
    19.00
     Jungle
    17.13
    summer
    16.50
    贫困
    16.38
    骚
    16.13
     gruesome
    16.13
    集团旗下
    16.13
    edException
    15.88
    _GROUPS
    15.88
    童年
    15.81
    Activations Density 0.797%

    No Known Activations