© 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. 11-RESID-POST-AA
    6. 24860
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    滿足
    -0.08
    专利
    -0.07
    (address
    -0.06
     Replace
    -0.06
     word
    -0.06
    ×
    -0.06
    履
    -0.06
      ↵↵
    -0.06
    登陆
    -0.06
     tap
    -0.06
    POSITIVE LOGITS
    draul
    0.08
    	Transform
    0.08
     nữa
    0.08
     Processes
    0.07
    播出
    0.07
    _profit
    0.07
     sehr
    0.07
    琭
    0.07
     Klan
    0.07
     скач
    0.07
    Activations Density 0.002%

    No Known Activations