© 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. 16067
    Prev
    Next
    INDEX
    Explanations

    risk reduction

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

    No Comments

    Negative Logits
    ��
    -21.25
    qr
    -15.88
     Qatar
    -15.44
    és
    -15.00
    倩
    -14.50
    惕
    -14.38
    匮
    -14.19
    圣经
    -14.06
    -character
    -13.94
    umper
    -13.75
    POSITIVE LOGITS
    рог
    16.50
    udo
    16.25
    icc
    16.13
    中标
    16.13
    indle
    16.13
     Labels
    15.94
    uron
    15.75
    reno
    15.38
    ogl
    15.31
     tags
    15.06
    Activations Density 0.227%

    No Known Activations