© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 209
    Prev
    Next
    INDEX
    Explanations

    Harbin references

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    晋江
    -22.75
    珙
    -22.63
     SCE
    -22.00
    宜宾
    -21.00
    雒
    -20.75
    福建省
    -20.13
    泉州
    -19.88
     Cupertino
    -19.13
    山西省
    -19.00
     AFC
    -18.88
    POSITIVE LOGITS
    哈
    53.00
    哈尔滨
    44.25
     HASH
    43.50
    (hash
    40.25
     hash
    39.25
     Hash
    38.25
    黑龙江
    37.00
    黑龙江省
    37.00
     hashes
    36.25
    	hash
    35.50
    Activations Density 0.070%

    No Known Activations