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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 57218
    Prev
    Next
    INDEX
    Explanations

    Makeup, especially blush

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ➿
    -0.09
    罔
    -0.07
    ⅅ
    -0.07
    瀼
    -0.07
    𪤗
    -0.07
     clarification
    -0.07
     mưa
    -0.07
    ☬
    -0.07
    折磨
    -0.07
    𝑑
    -0.06
    POSITIVE LOGITS
     premiered
    0.08
    针
    0.07
    Objective
    0.07
    0.07
     ม
    0.07
    高新技术
    0.07
    法定代表
    0.06
    מק
    0.06
    0.06
    REAK
    0.06
    Activations Density 0.002%

    No Known Activations