Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 111083
    Prev
    Next
    INDEX
    Explanations

    Website content/sharing

    np_max-act · gemini-2.0-flash

    UI/navigation elements and metadata on a webpage (e.g., "Image", "Share", "Page", sponsored/image credits).

    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_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
    ardy
    -0.07
     fare
    -0.07
     Crime
    -0.07
    .fl
    -0.07
    .routes
    -0.07
     recycl
    -0.07
     adip
    -0.06
    날
    -0.06
     gluc
    -0.06
     обязан
    -0.06
    POSITIVE LOGITS
    itas
    0.07
    _validator
    0.07
    achen
    0.07
     casa
    0.07
    安装
    0.07
    城市管理
    0.07
     państw
    0.07
     questão
    0.07
     banning
    0.07
    相助
    0.07
    Activations Density 0.041%

    No Known Activations