© 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. 14804
    Prev
    Next
    INDEX
    Explanations

    say "th"

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

    No Comments

    Negative Logits
    案
    -17.75
    enarios
    -16.13
    entifier
    -15.63
    一体
    -15.44
    TemplateName
    -15.44
    Functions
    -15.38
    供求
    -14.75
    Scenario
    -14.56
     LaTeX
    -14.50
    lem
    -14.25
    POSITIVE LOGITS
    ndl
    18.13
    orb
    17.38
    ORB
    16.88
     fz
    16.50
    dek
    15.63
    /kernel
    15.50
    kbd
    15.00
     INDIRECT
    14.94
    kel
    14.94
    imest
    14.50
    Activations Density 0.030%

    No Known Activations