© 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. 2415
    Prev
    Next
    INDEX
    Explanations

    seq

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

    No Comments

    Negative Logits
    @register
    -17.88
    _register
    -17.00
    资本
    -16.38
    (register
    -16.25
     REGISTER
    -16.13
    са
    -16.13
     register
    -15.88
     Register
    -15.81
    	Register
    -15.69
    改革
    -15.00
    POSITIVE LOGITS
     seq
    58.50
    (seq
    49.50
    seq
    49.50
    .seq
    46.75
     Seq
    46.50
    	seq
    45.75
    Seq
    45.00
    _seq
    42.50
     SEQ
    38.00
    eq
    36.00
    Activations Density 0.023%

    No Known Activations