© 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 EvalsExportsinterp-engineNEWAPI 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. 5474
    Prev
    Next
    INDEX
    Explanations

    reflection mirrors

    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
     profession
    -0.07
    .rightBarButtonItem
    -0.07
    שדה
    -0.07
    atore
    -0.07
     getSize
    -0.07
     archivo
    -0.07
    📔
    -0.07
     stout
    -0.07
    <Self
    -0.06
    支柱
    -0.06
    POSITIVE LOGITS
    ール
    0.08
    ANEL
    0.07
    nal
    0.07
    عار
    0.07
    .call
    0.07
    rack
    0.07
    刘某
    0.07
    acial
    0.07
    奥巴马
    0.07
    滴滴
    0.07
    Activations Density 0.005%

    No Known Activations