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. 129678
    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
    نطق
    -0.08
     Subway
    -0.07
     Mozart
    -0.07
    anela
    -0.07
    椎
    -0.07
     thấy
    -0.07
     rusty
    -0.07
    샌
    -0.06
    	Resource
    -0.06
     Nikola
    -0.06
    POSITIVE LOGITS
     healer
    0.07
    欧
    0.07
     frag
    0.07
    🔕
    0.07
    即便
    0.07
     hides
    0.06
     erotico
    0.06
    戭
    0.06
    评委
    0.06
    相对
    0.06
    Activations Density 0.064%

    No Known Activations