© 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. 15338
    Prev
    Next
    INDEX
    Explanations

    technical terms

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

    No Comments

    Negative Logits
    бол
    -16.38
    .presenter
    -16.25
    陷阱
    -16.13
    Paint
    -15.75
    _difference
    -15.50
     Innoc
    -15.44
    真假
    -15.19
    _equals
    -14.75
    Exercise
    -14.50
    强奸
    -14.50
    POSITIVE LOGITS
     metav
    12.94
    psc
    12.06
    徘
    11.88
    筱
    11.75
    商业化
    11.56
     SSP
    11.50
    Ź
    11.25
     tslib
    11.06
    Ctl
    10.94
     γ
    10.88
    Activations Density 0.420%

    No Known Activations