© 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
    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. 116901
    Prev
    Next
    INDEX
    Explanations

    MSDN URLs

    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
    时时彩
    -0.08
     mol
    -0.07
    “How
    -0.07
     mụ
    -0.07
    👼
    -0.07
    闭
    -0.06
    <|im_start|>
    -0.06
     men
    -0.06
    imen
    -0.06
    起点
    -0.06
    POSITIVE LOGITS
    	Boolean
    0.07
     Peripheral
    0.07
    nces
    0.07
     Equals
    0.07
    .Toolbar
    0.07
    -article
    0.07
    몇
    0.06
    拿到了
    0.06
    لاقة
    0.06
    껌
    0.06
    Activations Density 0.001%

    No Known Activations