© 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. 2324
    Prev
    Next
    INDEX
    Explanations

    许

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

    No Comments

    Negative Logits
     poly
    -17.38
     pot
    -17.38
     RESET
    -16.75
    _pot
    -16.50
     metab
    -16.25
     Pot
    -16.00
    (poly
    -15.63
    poly
    -15.13
     LEG
    -15.00
     meds
    -14.81
    POSITIVE LOGITS
    许
    90.50
    許
    72.50
     em
    68.50
     Em
    63.00
    (em
    58.50
    	em
    58.50
    em
    58.00
    Em
    57.75
    _em
    57.50
    -em
    54.00
    Activations Density 0.049%

    No Known Activations