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. 109928
    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
     listItem
    -0.07
    	Status
    -0.07
    disk
    -0.07
    -param
    -0.07
    ),$
    -0.07
    迢
    -0.06
     Down
    -0.06
    .""
    -0.06
     Já
    -0.06
     نها
    -0.06
    POSITIVE LOGITS
    最重要的
    0.07
     prote
    0.07
    操纵
    0.07
    老龄化
    0.07
     biến
    0.07
    リング
    0.07
    מראה
    0.07
    NL
    0.06
    اعدة
    0.06
    萊
    0.06
    Activations Density 0.077%

    No Known Activations