Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 56693
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    court
    -0.08
    tempts
    -0.07
     PARK
    -0.07
    church
    -0.07
    рг
    -0.07
     purpos
    -0.06
    hunt
    -0.06
     FUNC
    -0.06
    請求
    -0.06
    ȱ
    -0.06
    POSITIVE LOGITS
    常年
    0.07
    _ctxt
    0.07
    讲解
    0.07
     proclamation
    0.07
    riages
    0.07
     estim
    0.07
     passing
    0.07
    席执行官
    0.07
    読み
    0.07
    igma
    0.07
    Activations Density 0.182%

    No Known Activations