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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 129436
    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
    課程
    -0.08
    pron
    -0.07
    Running
    -0.07
     Pharmac
    -0.07
    蓝
    -0.07
    文档
    -0.07
    掌握了
    -0.07
    ├
    -0.07
     이렇
    -0.06
    .warn
    -0.06
    POSITIVE LOGITS
    给力
    0.07
     finder
    0.07
     Теперь
    0.07
    쮮
    0.06
     rõ
    0.06
    不得
    0.06
     realistically
    0.06
    ');
    ↵
    0.06
    	handle
    0.06
     ribs
    0.06
    Activations Density 0.000%

    No Known Activations