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. 48364
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    欧美
    -0.07
     isLoggedIn
    -0.07
    eric
    -0.07
     Daddy
    -0.07
    ировал
    -0.07
    經
    -0.07
    .eu
    -0.07
    文
    -0.07
    伊
    -0.07
     giriş
    -0.06
    POSITIVE LOGITS
     Zimmer
    0.07
    _style
    0.07
    _scan
    0.07
     SEND
    0.06
    TOTAL
    0.06
    NJ
    0.06
    手册
    0.06
    ✸
    0.06
     الجمهور
    0.06
    挂号
    0.06
    Activations Density 0.088%

    No Known Activations