© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 2336
    Prev
    Next
    INDEX
    Explanations

    Advice/personal stories

    np_max-act · gemini-2.0-flash

    sentences or phrases that give advice, recommendations, or ask/pose questions addressed to the reader (second‑person directives and conditionals).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    メッセージ
    -0.07
    史上
    -0.07
    士兵
    -0.07
     Willis
    -0.07
    desktop
    -0.06
    ทหาร
    -0.06
     Hash
    -0.06
    qi
    -0.06
    貴
    -0.06
     Thai
    -0.06
    POSITIVE LOGITS
    ，并
    0.07
    sla
    0.07
    faker
    0.07
     nets
    0.07
    itledBorder
    0.07
    ")==
    0.07
    漫
    0.07
    更好地
    0.07
    黢
    0.07
    <<<<<<<<
    0.07
    Activations Density 0.222%

    No Known Activations