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. 60523
    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_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
     Вы
    -0.07
    قيادة
    -0.07
    fadeIn
    -0.07
     Jade
    -0.07
    ViewChild
    -0.07
    ateful
    -0.07
    白色的
    -0.07
    嘹
    -0.07
    .findById
    -0.06
     صباح
    -0.06
    POSITIVE LOGITS
    >>();↵↵
    0.07
    achievement
    0.07
     pequeño
    0.07
     enrollment
    0.06
    Closing
    0.06
    Warnings
    0.06
    신용
    0.06
    知识
    0.06
     jsonObject
    0.06
    ======↵
    0.06
    Activations Density 0.006%

    No Known Activations