© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 266
    Prev
    Next
    INDEX
    Explanations

    dinosaurs

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

    No Comments

    Negative Logits
    碳酸
    -18.63
    隧道
    -18.63
    磷
    -18.50
    椁
    -18.00
    洞
    -17.63
    枞
    -17.50
    acht
    -16.88
     drilled
    -16.63
    _hw
    -16.38
    CRY
    -16.13
    POSITIVE LOGITS
    DSL
    17.25
    zac
    17.13
     DSL
    16.50
    吞
    15.44
    公诉
    15.38
     allot
    15.38
    .Misc
    15.13
    ニック
    14.44
     Raleigh
    14.44
    好吃
    14.06
    Activations Density 0.048%

    No Known Activations