© 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. 15754
    Prev
    Next
    INDEX
    Explanations

    accommodation

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

    No Comments

    Negative Logits
     militar
    -21.38
    跳
    -20.13
     gyro
    -19.25
     pumps
    -19.25
     Milit
    -19.13
    跳跃
    -19.00
     turbo
    -19.00
    _lstm
    -18.75
    蹦
    -18.75
    水泵
    -18.50
    POSITIVE LOGITS
    .Cos
    17.88
    .um
    17.75
    _TXT
    17.63
    ums
    17.13
     umb
    16.88
    cos
    16.88
     Cos
    16.75
    笺
    16.75
    Convention
    16.63
     TEXT
    16.50
    Activations Density 1.525%

    No Known Activations