© 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. 63193
    Prev
    Next
    INDEX
    Explanations

    assistant reply headers and list-style answer scaffolding, especially enumerated formats and prominent numerals like years or item counts.

    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
     ром
    -0.08
    在一
    -0.07
    打造
    -0.07
    Billy
    -0.07
    处于
    -0.07
    timestamps
    -0.07
    借助
    -0.07
     ###
    -0.07
    شركة
    -0.07
     Zika
    -0.07
    POSITIVE LOGITS
     FR
    0.07
     inex
    0.07
    ᵔ
    0.07
    呣
    0.07
    酸
    0.07
    觉醒
    0.07
     urgency
    0.06
    URY
    0.06
    _PRIV
    0.06
     ActiveForm
    0.06
    Activations Density 0.219%

    No Known Activations