© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15633
    Prev
    Next
    INDEX
    Explanations

    say change

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

    No Comments

    Negative Logits
    海绵
    -18.00
    的压力
    -15.31
    竽
    -15.25
    袱
    -14.94
    _transient
    -14.75
    irates
    -14.56
    高峰期
    -14.44
    飞船
    -14.31
    élé
    -14.06
    蹿
    -14.06
    POSITIVE LOGITS
    修改
    45.75
    改动
    40.50
     modifications
    39.25
     modification
    38.75
    修正
    38.25
    修订
    38.00
    更改
    37.25
     edits
    36.75
     modifying
    35.75
    Modification
    35.75
    Activations Density 0.626%

    No Known Activations