© 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. 3078
    Prev
    Next
    INDEX
    Explanations

    transition

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

    No Comments

    Negative Logits
    例
    -17.38
    TB
    -16.25
    _TA
    -16.13
     TN
    -16.00
    TN
    -15.88
    сот
    -15.56
    社區
    -15.38
    _panel
    -15.38
    案件
    -15.19
    �
    -15.13
    POSITIVE LOGITS
     transition
    30.88
     transformation
    28.00
    transition
    27.38
     Transformation
    26.50
     Transition
    26.13
    Transition
    25.50
    transaction
    24.88
    Transaction
    24.63
     transaction
    24.13
     Transaction
    23.25
    Activations Density 0.199%

    No Known Activations