© 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. 2499
    Prev
    Next
    INDEX
    Explanations

    coefficients

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

    No Comments

    Negative Logits
    Mel
    -24.25
     Mel
    -24.00
     mel
    -23.88
    丁
    -23.13
    /demo
    -21.88
    Demo
    -21.63
    	reset
    -21.50
    reset
    -21.50
     net
    -20.88
     reset
    -20.50
    POSITIVE LOGITS
    apos
    16.00
     reciprocal
    15.00
    mag
    14.63
    ẫ
    14.56
    ponent
    14.44
    norm
    14.19
    _EQ
    14.06
    ESTAMP
    13.94
     norm
    13.50
     retain
    13.38
    Activations Density 0.176%

    No Known Activations