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. 11-RESID-POST-AA
    6. 21634
    Prev
    Next
    INDEX
    Explanations

    cannabis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etric
    -0.07
     Equipment
    -0.07
    srv
    -0.07
    用心
    -0.07
     rob
    -0.07
    海岛
    -0.07
    طف
    -0.06
    南宋
    -0.06
    选用
    -0.06
    山庄
    -0.06
    POSITIVE LOGITS
    🤩
    0.07
    ]',↵
    0.07
    -chief
    0.07
    -fin
    0.07
     '">'
    0.07
     fin
    0.07
     وج
    0.06
    /pi
    0.06
    全球化
    0.06
    骋
    0.06
    Activations Density 0.003%

    No Known Activations