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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 31393
    Prev
    Next
    INDEX
    Explanations

    diverse applications in industry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ไกล
    -0.08
     Geile
    -0.07
    /wait
    -0.07
     Simpson
    -0.07
    罗马
    -0.07
     conte
    -0.07
    ăr
    -0.07
    🐎
    -0.07
    Dyn
    -0.07
     Malk
    -0.07
    POSITIVE LOGITS
     considers
    0.08
    而对于
    0.07
    	build
    0.07
     //↵
    0.07
    да
    0.07
     experienced
    0.07
    及其
    0.07
    сли
    0.07
    可见
    0.07
     avoid
    0.07
    Activations Density 0.050%

    No Known Activations