© 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. 109831
    Prev
    Next
    INDEX
    Explanations

    Software development teamwork

    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
    Signature
    -0.08
     Validator
    -0.07
     laughed
    -0.07
    South
    -0.06
    镚
    -0.06
    实践中
    -0.06
    .Observable
    -0.06
    ampoline
    -0.06
     ")";↵
    -0.06
    football
    -0.06
    POSITIVE LOGITS
     Radi
    0.07
    ()>↵
    0.07
    ipers
    0.07
     элемент
    0.07
    if
    0.06
     adults
    0.06
     Они
    0.06
    كل
    0.06
     overlay
    0.06
    oji
    0.06
    Activations Density 0.063%

    No Known Activations