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. 77955
    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
    しい
    -0.07
    undai
    -0.07
    ],[
    -0.07
    raphic
    -0.07
    קבוצ
    -0.06
    צביע
    -0.06
    新冠病毒
    -0.06
     Champion
    -0.06
     Hữu
    -0.06
    ביץ
    -0.06
    POSITIVE LOGITS
    >');↵
    0.08
    設備
    0.07
     endure
    0.07
    票价
    0.07
    NORMAL
    0.07
     overlooked
    0.07
    峧
    0.07
    EH
    0.07
    耐用
    0.07
     meals
    0.07
    Activations Density 0.014%

    No Known Activations