© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    index

    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
    搜集
    -0.07
     trả
    -0.06
     jokes
    -0.06
    翔
    -0.06
     Diamond
    -0.06
     Drag
    -0.06
    жи
    -0.06
    story
    -0.06
     AJAX
    -0.06
     locator
    -0.06
    POSITIVE LOGITS
    別の
    0.07
     CH
    0.07
    温暖
    0.07
     chaired
    0.07
    柑
    0.07
    ဿ
    0.07
    -cols
    0.06
     CAM
    0.06
    龁
    0.06
    _pm
    0.06
    Activations Density 0.012%

    No Known Activations