© 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. 103244
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     ").
    -0.07
     Tim
    -0.07
     Programmer
    -0.07
     ])↵
    -0.07
     参数
    -0.07
    ados
    -0.07
    าร
    -0.07
    კ
    -0.07
    涉及到
    -0.07
    า
    -0.06
    POSITIVE LOGITS
    奇迹
    0.07
    绩效
    0.07
    opolitan
    0.07
    欧式
    0.07
     rhetoric
    0.07
     rallied
    0.07
    𝐅
    0.07
     узна
    0.06
     mixer
    0.06
     politics
    0.06
    Activations Density 0.186%

    No Known Activations