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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 121041
    Prev
    Next
    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quanto
    -0.08
     yet
    -0.07
     ear
    -0.07
     perspective
    -0.07
    ):
    -0.07
    pic
    -0.07
     hopefully
    -0.07
    TOTAL
    -0.07
     CMD
    -0.07
    .GridView
    -0.07
    POSITIVE LOGITS
    垱
    0.07
    .getInput
    0.07
    الته
    0.07
    בדיקות
    0.07
    坐落于
    0.07
    ܈
    0.07
    הזמנה
    0.07
     grievances
    0.06
    การออกแบบ
    0.06
    打交道
    0.06
    Activations Density 0.001%

    No Known Activations