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

    Neuronpedia

    Jacobian LensNEW
    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. 15-RESID-POST-AA
    11. 112673
    Prev
    Next
    INDEX
    Explanations

    assistants, pages, simulations

    np_max-act · gemini-2.0-flash

    statements where the speaker identifies themselves as an AI assistant, especially within chat-style dialogue.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    Imagen
    -0.08
    かい
    -0.07
     Hazel
    -0.07
    vasive
    -0.07
    .Products
    -0.07
    agraph
    -0.07
    薇
    -0.06
    ものが
    -0.06
    进行了
    -0.06
    wp
    -0.06
    POSITIVE LOGITS
    地形
    0.07
     malls
    0.07
    喉咙
    0.07
     דיגיטלי
    0.06
    restaurant
    0.06
    的投资
    0.06
    🚉
    0.06
    سياسات
    0.06
     sanct
    0.06
     trips
    0.06
    Activations Density 0.022%

    No Known Activations