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

    Neuronpedia

    APICircuit 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. 71652
    Prev
    Next
    INDEX
    Explanations

    privileged

    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
    囔
    -0.06
    🅴
    -0.06
    每一个人
    -0.06
    📛
    -0.06
    澎湃
    -0.06
     runners
    -0.06
     enthusiasts
    -0.06
    静电
    -0.06
    잖아요
    -0.06
    股本
    -0.06
    POSITIVE LOGITS
     Cleaning
    0.07
    融资租赁
    0.07
    DR
    0.07
    -utils
    0.07
     Lunch
    0.07
     Works
    0.06
    דת
    0.06
     MSR
    0.06
    อากาศ
    0.06
     β
    0.06
    Activations Density 0.001%

    No Known Activations