© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 41696
    Prev
    Next
    INDEX
    Explanations

    product configuration

    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
    얍
    -0.07
     ByteArrayInputStream
    -0.06
     süreç
    -0.06
    超额
    -0.06
    (WIN
    -0.06
    管理人员
    -0.06
    可视化
    -0.06
    上午
    -0.06
    .xmlbeans
    -0.06
    🗽
    -0.06
    POSITIVE LOGITS
    כת
    0.09
    -name
    0.07
    再去
    0.07
    /board
    0.07
     grote
    0.07
    .channels
    0.07
    一棵
    0.07
    rece
    0.06
    -ind
    0.06
    开户
    0.06
    Activations Density 0.071%

    No Known Activations