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. 1502
    Prev
    Next
    INDEX
    Explanations

    diagram

    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_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
    正值
    -0.07
    過ぎ
    -0.07
    较多
    -0.07
    Ctx
    -0.07
    Enter
    -0.07
    (J
    -0.07
     Reg
    -0.07
    经济
    -0.07
    支
    -0.07
    减
    -0.07
    POSITIVE LOGITS
     diagram
    0.09
     diagrams
    0.08
     الإنترنت
    0.07
    .radians
    0.07
    图像
    0.07
    aling
    0.07
    系列产品
    0.07
    明亮
    0.07
     splitter
    0.07
     kas
    0.07
    Activations Density 0.004%

    No Known Activations