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. 36428
    Prev
    Next
    INDEX
    Explanations

    Describing situations/events

    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
     loud
    -0.06
    �
    -0.06
    腰
    -0.06
    .dataset
    -0.06
    -photo
    -0.06
    楯
    -0.06
     parameter
    -0.06
    拇指
    -0.06
     مو
    -0.06
     burgeoning
    -0.06
    POSITIVE LOGITS
    “A
    0.09
     UIImagePickerController
    0.08
    "]=$
    0.08
      
    ↵
    ↵
    0.08
     Greece
    0.07
    _SERVER
    0.07
    ��
    0.07
    _AURA
    0.07
    价格上涨
    0.07
    地区的
    0.07
    Activations Density 0.130%

    No Known Activations