© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15803
    Prev
    Next
    INDEX
    Explanations

    say link

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

    No Comments

    Negative Logits
    年级
    -17.25
    日产
    -16.63
    木质
    -15.94
    羧
    -15.63
    acen
    -15.44
    .Mesh
    -15.25
    高峰
    -15.19
    _FLUSH
    -15.06
    shelf
    -15.00
    椎
    -14.94
    POSITIVE LOGITS
     link
    41.50
     links
    40.00
     Link
    39.25
     hyperlink
    38.50
    link
    38.00
    -link
    37.50
    リンク
    37.50
    链接
    37.50
    (link
    37.50
    	link
    37.00
    Activations Density 0.186%

    No Known Activations