© 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. 15406
    Prev
    Next
    INDEX
    Explanations

    say "ez"

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

    No Comments

    Negative Logits
    ellipse
    -21.38
    瞪
    -19.63
    blink
    -19.50
     blinking
    -19.50
     rebound
    -19.50
    的眼睛
    -19.38
     blink
    -19.25
     flashback
    -18.88
    甩
    -18.88
    眼神
    -18.50
    POSITIVE LOGITS
     coal
    23.00
    煤
    21.50
     Coal
    21.00
     Brass
    18.38
    煤炭
    18.25
    Oil
    18.13
    bra
    17.88
    淳
    17.75
    Coal
    17.63
     dairy
    17.25
    Activations Density 1.360%

    No Known Activations