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. 10808
    Prev
    Next
    INDEX
    Explanations

    pasta

    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
    ügen
    -0.07
    行使
    -0.07
    ║
    -0.06
    −
    -0.06
    的确是
    -0.06
    �
    -0.06
    去
    -0.06
    替换
    -0.06
     cấp
    -0.06
    یر
    -0.06
    POSITIVE LOGITS
    斯塔
    0.08
     Southampton
    0.08
    URLRequest
    0.07
    联合国
    0.07
    琬
    0.07
     Boca
    0.07
     Frankfurt
    0.07
     Andrea
    0.07
    noopener
    0.07
    {}↵
    0.07
    Activations Density 0.004%

    No Known Activations