© 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
    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. 52874
    Prev
    Next
    INDEX
    Explanations

    legal/juridical terminology and references to law, justice, or legal professions and studies (often in German but also across languages).

    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
    OutOfRange
    -0.07
    ď
    -0.07
    _ng
    -0.07
    зав
    -0.07
    еть
    -0.07
    ная
    -0.07
    Ⓔ
    -0.07
    新しい
    -0.07
    nde
    -0.06
    岑
    -0.06
    POSITIVE LOGITS
    .AddScoped
    0.08
    治理体系
    0.08
     ENTITY
    0.07
    مور
    0.07
    .gridx
    0.07
     Protect
    0.07
    UBLISH
    0.07
     TAX
    0.07
     migrated
    0.07
     hashes
    0.07
    Activations Density 0.051%

    No Known Activations