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. 14422
    Prev
    Next
    INDEX
    Explanations

    statistical ratios

    np_max-act · gemini-2.0-flash
    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
     Vertex
    -0.07
    apped
    -0.07
     결
    -0.07
     Conclusion
    -0.07
     jeg
    -0.07
    "sync
    -0.06
    "strconv
    -0.06
    خت
    -0.06
     문자
    -0.06
     Choices
    -0.06
    POSITIVE LOGITS
     conspiracy
    0.07
     becoming
    0.07
     wee
    0.07
    勃勃
    0.07
     Underground
    0.07
    オリ
    0.07
    :'',↵
    0.06
    steen
    0.06
    廳
    0.06
     colorful
    0.06
    Activations Density 0.042%

    No Known Activations