© 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 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. 62772
    Prev
    Next
    INDEX
    Explanations

    requests to “answer/reply,” especially imperatives across multiple languages and prompts asking for answers in a specific language.

    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
     pc
    -0.07
     Panama
    -0.07
     house
    -0.07
     пере
    -0.07
     ],
    -0.07
    🌠
    -0.07
     הנה
    -0.07
     WCHAR
    -0.07
     потом
    -0.07
     Author
    -0.07
    POSITIVE LOGITS
    leftJoin
    0.08
    🤷
    0.07
    toa
    0.07
    Wei
    0.07
    fid
    0.07
    犏
    0.07
    诿
    0.07
    RTOS
    0.07
    ⎦
    0.06
    𐍂
    0.06
    Activations Density 0.218%

    No Known Activations