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. 60151
    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
    竞价
    -0.07
     pharmac
    -0.07
     poc
    -0.06
    睦
    -0.06
    otp
    -0.06
    赌博
    -0.06
     document
    -0.06
     Chính
    -0.06
     Decision
    -0.06
    isclosed
    -0.06
    POSITIVE LOGITS
    쎌
    0.07
     Keller
    0.07
    ลาน
    0.07
     theta
    0.07
    flower
    0.07
    Indian
    0.06
     stylish
    0.06
     семей
    0.06
     gerne
    0.06
     pendant
    0.06
    Activations Density 0.002%

    No Known Activations