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. 7062
    Prev
    Next
    INDEX
    Explanations

    for

    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
    .tile
    -0.07
    庆
    -0.07
    مناطق
    -0.06
     pesquisa
    -0.06
     רשימת
    -0.06
    该院
    -0.06
     topped
    -0.06
     cidade
    -0.06
    ქ
    -0.06
     Util
    -0.06
    POSITIVE LOGITS
     Latvia
    0.09
    Fast
    0.09
    Creators
    0.07
     cautiously
    0.07
    IMIZE
    0.07
    CONN
    0.07
    ڔ
    0.07
     Mu
    0.07
    信息系统
    0.07
    vanced
    0.07
    Activations Density 0.016%

    No Known Activations