© 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. 15-RESID-POST-AA
    11. 72137
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    띔
    -0.07
    旅
    -0.07
     fruitful
    -0.07
     Drugs
    -0.07
    etween
    -0.07
    骟
    -0.07
    何度
    -0.07
     grappling
    -0.07
    hips
    -0.06
    คร
    -0.06
    POSITIVE LOGITS
     DB
    0.07
     数据
    0.07
    outcome
    0.07
     ax
    0.07
    틑
    0.07
    ДЕ
    0.07
    !"
    0.07
    (id
    0.07
    電子
    0.07
    \"";↵
    0.07
    Activations Density 0.013%

    No Known Activations