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. 23-RESID-POST-AA
    6. 130561
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anne
    -0.08
     meine
    -0.07
    入手
    -0.07
    ㅜ
    -0.06
    pción
    -0.06
    <pcl
    -0.06
    👟
    -0.06
    と思い
    -0.06
    朗诵
    -0.06
    -Cola
    -0.06
    POSITIVE LOGITS
    🥀
    0.07
    det
    0.07
    Extend
    0.06
     Collabor
    0.06
    \(
    0.06
    相关内容
    0.06
    stdout
    0.06
    _"
    0.06
    	record
    0.06
     ''
    0.06
    Activations Density 0.187%

    No Known Activations