© 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. 15-RESID-POST-AA
    11. 13408
    Prev
    Next
    INDEX
    Explanations

    Comic book characters

    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
     keen
    -0.07
    ŀ
    -0.07
    ً
    -0.07
    學
    -0.07
    意见反馈
    -0.06
     bred
    -0.06
     تعتبر
    -0.06
    .']
    -0.06
    Marks
    -0.06
     Pee
    -0.06
    POSITIVE LOGITS
     adjustment
    0.07
    rectangle
    0.07
     모든
    0.06
     AN
    0.06
    幸福
    0.06
    halten
    0.06
    加工
    0.06
    调整
    0.06
    겊
    0.06
    replace
    0.06
    Activations Density 0.031%

    No Known Activations