© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3069
    Prev
    Next
    INDEX
    Explanations

    say subscript characters

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

    No Comments

    Negative Logits
     cert
    -19.25
     simul
    -19.13
     config
    -18.88
     sim
    -18.63
    模拟
    -18.50
     sims
    -18.38
    (config
    -17.75
    .config
    -17.50
     configs
    -17.25
    防
    -17.13
    POSITIVE LOGITS
    �
    26.50
    ��
    26.38
    �
    26.38
    ���
    26.38
    �
    25.75
    ����
    23.00
    �s
    23.00
     ����
    22.63
     �
    22.63
    ____
    21.38
    Activations Density 0.016%

    No Known Activations