© 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. 14766
    Prev
    Next
    INDEX
    Explanations

    say "increase"

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

    No Comments

    Negative Logits
    移动
    -18.88
    _ARR
    -17.13
     front
    -15.63
    лем
    -15.56
    Unload
    -15.50
    _nr
    -15.38
    ARRAY
    -15.38
     loaders
    -15.25
    -front
    -14.94
    uos
    -14.88
    POSITIVE LOGITS
    创建
    15.31
    created
    14.31
     creat
    14.19
    creation
    14.13
    炸
    14.06
    ечен
    14.00
    ResultsController
    13.75
     创建
    13.69
    .creation
    13.69
    control
    13.56
    Activations Density 0.131%

    No Known Activations