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. 56441
    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
    publish
    -0.07
    _task
    -0.07
     obscure
    -0.07
    untas
    -0.07
     cabo
    -0.07
     Geliş
    -0.07
    语言
    -0.07
    Lie
    -0.07
    (Frame
    -0.07
    aso
    -0.07
    POSITIVE LOGITS
    💘
    0.08
    大酒店
    0.07
    机械设备
    0.07
    🏖
    0.07
    ")));
    ↵
    0.07
    -type
    0.07
     plated
    0.07
     Folding
    0.07
    Ƌ
    0.06
     birç
    0.06
    Activations Density 0.157%

    No Known Activations