© 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. 1576
    Prev
    Next
    INDEX
    Explanations

    say "noise"

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

    No Comments

    Negative Logits
    图书馆
    -55.00
     library
    -52.50
     libraries
    -52.25
     Library
    -48.50
     Libraries
    -48.50
    library
    -47.25
    Library
    -45.75
    libraries
    -42.25
    -library
    -41.75
    .Library
    -41.25
    POSITIVE LOGITS
    _noise
    14.44
     Noise
    14.44
    驹
    14.31
     beau
    14.00
     noise
    13.94
    声
    13.81
    Noise
    13.69
    Orm
    13.69
    noise
    13.63
     SOUND
    13.63
    Activations Density 0.106%

    No Known Activations