© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 57061
    Prev
    Next
    INDEX
    Explanations

    amide

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leod
    -0.07
    ]==
    -0.07
    有关
    -0.07
    شار
    -0.07
     NVIC
    -0.06
    Supplier
    -0.06
     chứng
    -0.06
    警告
    -0.06
     HDF
    -0.06
    ibel
    -0.06
    POSITIVE LOGITS
     информация
    0.07
     см
    0.07
    帆
    0.07
    Description
    0.07
    sort
    0.07
    Sort
    0.06
     $('
    0.06
     contexto
    0.06
    ᵉ
    0.06
    春风
    0.06
    Activations Density 0.001%

    No Known Activations