© 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. 15-RESID-POST-AA
    6. 11066
    Prev
    Next
    INDEX
    Explanations

    true/alleged

    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
     warned
    -0.07
     rn
    -0.07
    듦
    -0.07
     dürfen
    -0.07
    الت
    -0.07
    ʾ
    -0.07
     sugars
    -0.07
    כיון
    -0.07
     promoted
    -0.06
    ieval
    -0.06
    POSITIVE LOGITS
    的数据
    0.07
    的对象
    0.07
    _makeConstraints
    0.07
    .ai
    0.07
     attachment
    0.07
     partially
    0.07
    物流公司
    0.07
    دراج
    0.07
     {})↵
    0.07
     thêm
    0.07
    Activations Density 0.013%

    No Known Activations