© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2393
    Prev
    Next
    INDEX
    Explanations

    say "init"

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

    No Comments

    Negative Logits
    gee
    -17.25
     DPI
    -15.81
    otte
    -15.81
    iali
    -15.50
    combe
    -15.19
    RIA
    -14.81
    reservation
    -14.63
     Bliss
    -14.56
    otti
    -14.44
    oti
    -14.44
    POSITIVE LOGITS
    init
    66.50
     init
    63.00
     Init
    62.75
    Init
    62.75
    (init
    58.25
    .init
    54.75
    	init
    54.50
    -init
    54.00
    _init
    50.00
    .Init
    49.75
    Activations Density 0.225%

    No Known Activations