© 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. 2200
    Prev
    Next
    INDEX
    Explanations

    say "bool"

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

    No Comments

    Negative Logits
    emin
    -18.88
     Perkins
    -18.25
    反射
    -18.00
    定量
    -17.50
     Miranda
    -17.38
    曲
    -17.25
    /ref
    -17.00
    Fuse
    -17.00
     refin
    -16.88
    共振
    -16.88
    POSITIVE LOGITS
     bool
    31.75
     Bool
    31.38
    Bool
    30.00
    ,bool
    27.50
    (bool
    25.63
    bool
    25.38
    	bool
    25.13
    =bool
    24.25
     Ber
    23.88
    _bool
    23.75
    Activations Density 0.060%

    No Known Activations