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. 6984
    Prev
    Next
    INDEX
    Explanations

    say "))"

    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
     tentative
    -0.06
     setDefaultCloseOperation
    -0.06
    outfile
    -0.06
    出游
    -0.06
    抵御
    -0.06
     uLocal
    -0.06
    运算
    -0.06
    �
    -0.06
     {...
    -0.06
    不排除
    -0.06
    POSITIVE LOGITS
    .authorization
    0.08
    .pro
    0.07
     posted
    0.07
     serum
    0.07
    �
    0.07
    Board
    0.07
     Greene
    0.07
    erializer
    0.07
     dụng
    0.07
    标配
    0.07
    Activations Density 0.003%

    No Known Activations