© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 127639
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    edReader
    -0.07
     удален
    -0.07
    并非
    -0.07
     obligated
    -0.07
    헵
    -0.07
    なんで
    -0.07
    	items
    -0.07
    一度
    -0.07
    所提供之
    -0.07
     Isa
    -0.07
    POSITIVE LOGITS
     Purchase
    0.08
    研究中心
    0.08
    Touchable
    0.07
    狠
    0.07
     research
    0.07
     Bust
    0.07
    ߗ
    0.07
     aria
    0.07
    腐
    0.07
    Clin
    0.07
    Activations Density 0.083%

    No Known Activations