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. 15-RESID-POST-AA
    6. 77786
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宄
    -0.08
     mejores
    -0.07
    릴
    -0.07
    ประส
    -0.07
    궜
    -0.07
     lança
    -0.07
    횰
    -0.07
     Analysis
    -0.06
    媂
    -0.06
    ঔ
    -0.06
    POSITIVE LOGITS
    _tasks
    0.07
     אר
    0.07
     landscaping
    0.07
    投票
    0.07
     Wallet
    0.07
    🌶
    0.07
    .machine
    0.07
    飯
    0.07
    减速
    0.06
     tệ
    0.06
    Activations Density 0.197%

    No Known Activations