© 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. 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. 73527
    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
    Not in Any Lists

    No Comments

    Negative Logits
    תבר
    -0.07
    sequences
    -0.07
    رم
    -0.07
     Predictor
    -0.07
     Dickens
    -0.07
    arget
    -0.07
    _Event
    -0.07
    تحق
    -0.07
    picked
    -0.07
     hide
    -0.06
    POSITIVE LOGITS
    我市
    0.07
    齊
    0.07
     טבעי
    0.07
    _MM
    0.07
     =[
    0.07
    采用
    0.06
     Enhancement
    0.06
    介绍说
    0.06
     продукции
    0.06
     محافظ
    0.06
    Activations Density 0.373%

    No Known Activations