© 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. 16117
    Prev
    Next
    INDEX
    Explanations

    say non-Latin characters

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

    No Comments

    Negative Logits
     SX
    -42.50
    -s
    -40.75
    SA
    -39.50
    -S
    -38.75
     SAC
    -38.25
    SX
    -38.25
    桑
    -38.25
     SA
    -38.00
    萨
    -37.00
     SJ
    -36.75
    POSITIVE LOGITS
    朵
    14.38
    잡
    13.19
    فوض
    13.13
    镦
    12.94
    岐
    12.75
    翎
    12.75
    ammable
    12.69
    bz
    12.44
    镀锌
    12.00
    町
    11.94
    Activations Density 5.329%

    No Known Activations