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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 130922
    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
     dific
    -0.08
    毛泽
    -0.08
    䴥
    -0.07
    ("-");↵
    -0.07
     поч
    -0.07
    无线电
    -0.07
    <Cell
    -0.07
    uyến
    -0.07
     тех
    -0.07
     HttpStatusCode
    -0.07
    POSITIVE LOGITS
    官
    0.08
    視
    0.07
    ı
    0.07
     ghost
    0.07
    王爷
    0.07
     ignore
    0.07
     kị
    0.07
     split
    0.07
    邀请
    0.07
    	run
    0.07
    Activations Density 0.013%

    No Known Activations