© 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. 60464
    Prev
    Next
    INDEX
    Explanations

    Instances of direct second-person address (especially "you") — typically sentences giving advice or urging the reader to seek medical attention.

    oai_token-act-pair · gpt-5-miniTriggered 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
    ",
    -0.08
    יק
    -0.07
     dubious
    -0.07
    "x
    -0.07
    ”)
    -0.07
    딧
    -0.07
    荡
    -0.06
    大奖
    -0.06
    ').
    -0.06
     ل
    -0.06
    POSITIVE LOGITS
     cellphone
    0.07
    胲
    0.07
    佖
    0.07
    闺蜜
    0.07
     realiza
    0.07
    できません
    0.07
     setInterval
    0.07
     фот
    0.07
     ethers
    0.07
    alsy
    0.07
    Activations Density 0.046%

    No Known Activations