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. 13898
    Prev
    Next
    INDEX
    Explanations

    C++ code, macros

    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_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
    maxcdn
    -0.07
    page
    -0.07
     BLE
    -0.07
    bc
    -0.07
    流程
    -0.07
    	MD
    -0.07
     Reload
    -0.06
    (rule
    -0.06
     subscription
    -0.06
     Courses
    -0.06
    POSITIVE LOGITS
    _whitespace
    0.08
    泌
    0.07
     безопас
    0.07
     Exists
    0.07
    INU
    0.07
    出自
    0.07
    胶囊
    0.06
    _oper
    0.06
    .Design
    0.06
    嗪
    0.06
    Activations Density 0.017%

    No Known Activations