© 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. 3164
    Prev
    Next
    INDEX
    Explanations

    say %

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     equation
    -17.00
    postId
    -16.63
    子
    -16.50
    一道
    -16.13
    ActionButton
    -16.00
    子里
    -15.44
    _band
    -15.19
    (endpoint
    -15.06
    -handler
    -14.88
    osph
    -14.69
    POSITIVE LOGITS
     %
    21.88
    模型
    17.25
    range
    17.13
     range
    17.00
     model
    16.75
     form
    16.50
     block
    16.50
    现场
    16.50
    Range
    16.50
     Block
    16.38
    Activations Density 0.021%

    No Known Activations