© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14587
    Prev
    Next
    INDEX
    Explanations

    say 1

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

    No Comments

    Negative Logits
     Gir
    -16.63
    	Py
    -15.50
    /py
    -15.44
     Vog
    -15.25
    igkeit
    -15.00
    �数
    -14.75
     GIR
    -14.69
    	Grid
    -14.56
    .adapter
    -14.50
    	cfg
    -14.50
    POSITIVE LOGITS
     swal
    15.88
    师
    15.38
    hr
    15.25
    hl
    15.25
    aru
    15.00
    KM
    14.81
    哈尔
    14.63
    ialis
    14.50
    HU
    14.50
    ha
    14.38
    Activations Density 0.026%

    No Known Activations