© 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. 11-RESID-POST-AA
    11. 69785
    Prev
    Next
    INDEX
    Explanations

    CD

    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
    ('.
    -0.07
     multiline
    -0.07
    (equalTo
    -0.06
     getImage
    -0.06
    头疼
    -0.06
     szcz
    -0.06
    unsafe
    -0.06
     Delhi
    -0.06
    :]↵↵
    -0.06
    嗍
    -0.06
    POSITIVE LOGITS
    的人物
    0.07
     light
    0.07
    统筹推进
    0.07
    angkan
    0.07
    舰队
    0.07
    ery
    0.07
    بدء
    0.07
     Cette
    0.07
     commercially
    0.07
     usable
    0.06
    Activations Density 0.005%

    No Known Activations