© 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. 20992
    Prev
    Next
    INDEX
    Explanations

    code/markup

    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
    _UNUSED
    -0.07
    )++;↵
    -0.07
    _STORE
    -0.07
     seamless
    -0.07
     Dodge
    -0.07
    通关
    -0.07
     nóng
    -0.07
    黟
    -0.07
     NYC
    -0.06
    _service
    -0.06
    POSITIVE LOGITS
    resent
    0.07
    租房
    0.07
    经常会
    0.07
    istant
    0.07
    -writing
    0.06
    izzato
    0.06
    PLAN
    0.06
    IÊ
    0.06
    leneck
    0.06
    퍿
    0.06
    Activations Density 0.057%

    No Known Activations