© 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. 11-RESID-POST-AA
    6. 65714
    Prev
    Next
    INDEX
    Explanations

    problem

    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
    你们
    -0.08
    了一个
    -0.08
    在美国
    -0.08
     `${
    -0.08
    我现在
    -0.07
     terrible
    -0.07
    ========
    -0.07
    本当
    -0.07
    攝
    -0.07
    但是对于
    -0.07
    POSITIVE LOGITS
    leet
    0.07
    深情
    0.07
     Parm
    0.07
     çer
    0.07
    퀅
    0.06
    :Int
    0.06
    芳香
    0.06
    ลม
    0.06
    نق
    0.06
    La
    0.06
    Activations Density 0.061%

    No Known Activations