© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 77291
    Prev
    Next
    INDEX
    Explanations

    paragraph or section breaks—the boundaries where a new paragraph, subsection, footnote, or similar transition begins.

    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
    أحداث
    -0.07
    (){↵↵
    -0.07
    利于
    -0.07
    专项行动
    -0.07
     happening
    -0.07
    ']
    ↵
    ↵
    -0.07
     Checklist
    -0.07
     windows
    -0.06
    خلاف
    -0.06
    经营模式
    -0.06
    POSITIVE LOGITS
    owania
    0.07
    /power
    0.07
    /l
    0.07
    .sell
    0.07
    ilik
    0.07
    lararası
    0.07
     ECC
    0.07
    奕
    0.07
    Ст
    0.06
    Fed
    0.06
    Activations Density 0.188%

    No Known Activations