© 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. 2341
    Prev
    Next
    INDEX
    Explanations

    say diff

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

    No Comments

    Negative Logits
     regist
    -23.63
    注册
    -21.50
    (reg
    -21.38
    .Reg
    -21.13
    _registers
    -20.38
    REG
    -20.13
     regression
    -19.75
     Reg
    -19.63
    Reg
    -19.38
    reg
    -19.25
    POSITIVE LOGITS
     diff
    46.00
    diff
    37.50
     Diff
    36.00
    Diff
    33.75
    (diff
    33.00
    	diff
    31.63
     ref
    30.38
    .diff
    28.88
    _diff
    28.13
    	ref
    27.88
    Activations Density 0.057%

    No Known Activations