© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15395
    Prev
    Next
    INDEX
    Explanations

    say stable

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

    No Comments

    Negative Logits
     bli
    -17.88
    TransparentColor
    -17.75
    怨
    -16.38
    蘑菇
    -15.88
     misog
    -15.88
    .baidu
    -15.81
    妹妹
    -15.50
    妹子
    -15.50
    orias
    -15.44
    WebResponse
    -15.38
    POSITIVE LOGITS
    稳定
    48.75
    稳定性
    45.25
     stability
    44.75
    稳定的
    43.25
     stable
    43.00
    固定
    42.75
     Stability
    41.25
     fixed
    40.00
     stabil
    39.75
    穩定
    39.50
    Activations Density 0.399%

    No Known Activations