© 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. 64800
    Prev
    Next
    INDEX
    Explanations

    authoritative or coercive directives in dialogue—scenes where someone gives orders or demands and others are expected to comply.

    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
    加速
    -0.07
    けば
    -0.07
    ㈪
    -0.07
    silent
    -0.07
    FALSE
    -0.07
     валют
    -0.07
    =findViewById
    -0.07
    沸腾
    -0.07
    prend
    -0.07
    dge
    -0.07
    POSITIVE LOGITS
     genau
    0.07
     Bü
    0.07
     tw
    0.07
     Skyl
    0.07
     Kylie
    0.07
     onViewCreated
    0.06
    (file
    0.06
    ）
↵
    0.06
    ari
    0.06
    偷偷
    0.06
    Activations Density 0.191%

    No Known Activations