© 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. 16282
    Prev
    Next
    INDEX
    Explanations

    say nonsense

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

    No Comments

    Negative Logits
     Networks
    -16.88
    ksz
    -16.75
    键
    -16.50
     Cheryl
    -16.25
    (KeyEvent
    -15.94
    KeyEvent
    -15.75
    角
    -15.75
     JPEG
    -15.75
    璩
    -15.69
     Benny
    -15.63
    POSITIVE LOGITS
    荒
    19.88
    谬
    18.75
    Dummy
    18.25
     rubbish
    17.25
     error
    17.13
    垃圾
    17.13
     deco
    16.25
     garbage
    16.00
    mar
    16.00
    瞎
    15.69
    Activations Density 0.333%

    No Known Activations