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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1470
    Prev
    Next
    INDEX
    Explanations

    dust

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

    No Comments

    Negative Logits
     javascript
    -20.63
    艺术
    -18.38
    javascript
    -17.88
     artistic
    -17.50
     JavaScript
    -17.50
    JavaScript
    -16.75
     Javascript
    -16.50
     пес
    -16.13
    Javascript
    -16.13
    藝術
    -15.69
    POSITIVE LOGITS
     med
    30.50
     Med
    28.63
    Med
    28.25
    med
    25.88
    medi
    24.63
     medi
    24.38
    -med
    24.25
    _med
    24.25
     mediation
    23.00
     mediator
    22.75
    Activations Density 0.316%

    No Known Activations