© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1230
    Prev
    Next
    INDEX
    Explanations

    alloy

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

    No Comments

    Negative Logits
     athletic
    -17.13
    ồ
    -16.63
     athlete
    -16.63
     Dataset
    -16.25
    ån
    -16.25
     innovate
    -15.56
     innovative
    -15.50
    宫廷
    -15.50
    aghetti
    -15.38
    phas
    -14.94
    POSITIVE LOGITS
    Calc
    20.63
    Ca
    19.88
    glass
    19.00
    Glass
    18.88
     Ca
    18.88
     glass
    18.63
    _pc
    18.50
    德国
    18.50
    计算
    18.38
    钙
    18.38
    Activations Density 0.226%

    No Known Activations