Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 129791
    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
    Not in Any Lists

    No Comments

    Negative Logits
    أنظ
    -0.08
    Deletes
    -0.07
     qu
    -0.07
    ܓ
    -0.07
    奥林匹
    -0.07
    胡
    -0.07
     try
    -0.07
    macen
    -0.07
    非要
    -0.07
    Being
    -0.07
    POSITIVE LOGITS
     работ
    0.07
     التعليم
    0.07
    认真学习
    0.07
    >().
    0.07
     Titanium
    0.06
     overlooking
    0.06
    多媒体
    0.06
     renovations
    0.06
    课题
    0.06
    〳
    0.06
    Activations Density 0.010%

    No Known Activations