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. 130671
    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
     gust
    -0.07
    回顾
    -0.07
    每年都
    -0.07
    老師
    -0.06
    👏
    -0.06
    ongo
    -0.06
     grasp
    -0.06
    血液
    -0.06
     seguir
    -0.06
    (desc
    -0.06
    POSITIVE LOGITS
    Directive
    0.07
     centers
    0.07
    站点
    0.07
     liberté
    0.07
    Wh
    0.07
    Handler
    0.07
     Registers
    0.07
    javax
    0.07
    تنوع
    0.06
     sensit
    0.06
    Activations Density 0.079%

    No Known Activations