© 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. 15-RESID-POST-AA
    11. 78977
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or regulatory frameworks—rules, permissions, policies, laws, and compliance contexts, often tied to jurisdictions or official governance.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    注重
    -0.07
     hog
    -0.07
     бон
    -0.06
    (header
    -0.06
     maxX
    -0.06
     сохр
    -0.06
     ni
    -0.06
    確認
    -0.06
    睡觉
    -0.06
    (shell
    -0.06
    POSITIVE LOGITS
    吸引力
    0.07
     Bitte
    0.07
    ivar
    0.07
    不服
    0.07
     openness
    0.06
     brutality
    0.06
    👧
    0.06
    :m
    0.06
    {s
    0.06
    .att
    0.06
    Activations Density 0.273%

    No Known Activations