© 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. 11-RESID-POST-AA
    11. 84772
    Prev
    Next
    INDEX
    Explanations

    constitution

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    作物
    -0.07
     isActive
    -0.07
    �
    -0.07
     Ấn
    -0.07
    geme
    -0.07
    自主品牌
    -0.07
     municip
    -0.07
    _stmt
    -0.07
    줏
    -0.07
    מודע
    -0.07
    POSITIVE LOGITS
    (an
    0.08
     фото
    0.07
    thesis
    0.07
    +E
    0.07
    _logical
    0.07
     shift
    0.07
    reh
    0.06
     تقوم
    0.06
    	fwrite
    0.06
     răng
    0.06
    Activations Density 0.006%

    No Known Activations