© 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. 2501
    Prev
    Next
    INDEX
    Explanations

    say "安"

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

    No Comments

    Negative Logits
     Props
    -21.88
     PROP
    -21.63
     Prop
    -20.88
     propagation
    -20.50
    -prop
    -20.25
    _props
    -19.63
     Proposition
    -19.38
    RET
    -19.25
    _prop
    -19.00
     props
    -18.50
    POSITIVE LOGITS
    安
    71.00
    安县
    44.25
     �
    35.25
    (ans
    28.88
    安东
    27.00
    Ans
    26.50
     ant
    26.00
     Ans
    25.63
     ans
    25.50
    	ans
    24.13
    Activations Density 0.080%

    No Known Activations