© 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. 3075
    Prev
    Next
    INDEX
    Explanations

    say newline

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

    No Comments

    Negative Logits
    banks
    -15.50
    beam
    -15.38
    ¯
    -15.38
    群里
    -14.56
    rels
    -14.50
    pants
    -14.31
     facult
    -14.00
    电价
    -13.94
    uve
    -13.75
    支行
    -13.75
    POSITIVE LOGITS
     Ку
    15.69
     
↵
    15.13
    �
    14.19
    &#
    14.06
     
↵ 
↵
    14.00
    *</
    13.94
    érique
    13.94
    �
    13.94
     hair
    13.75
    ','%
    13.75
    Activations Density 0.115%

    No Known Activations