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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 12676
    Prev
    Next
    INDEX
    Explanations

    PDF

    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
     giants
    -0.07
    公平
    -0.07
    _prop
    -0.07
     xamarin
    -0.07
     использование
    -0.07
    孕妇
    -0.07
    嘈
    -0.07
    廉
    -0.07
    Coal
    -0.07
    اتحاد
    -0.07
    POSITIVE LOGITS
    的样子
    0.08
    askets
    0.07
    .Quantity
    0.07
    andise
    0.07
     catalogue
    0.07
    omez
    0.07
    .)↵↵
    0.07
    的通知
    0.06
     hurdle
    0.06
    .gstatic
    0.06
    Activations Density 0.055%

    No Known Activations