© 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. 64272
    Prev
    Next
    INDEX
    Explanations

    end-of-message chat delimiter tokens, especially the tag marking the end of a user turn.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    markers indicating the end of a user message in a chat transcript.

    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
     visiting
    -0.07
    -pad
    -0.06
     yc
    -0.06
    	driver
    -0.06
     Watching
    -0.06
    (GTK
    -0.06
     wre
    -0.06
     VIEW
    -0.06
    ץ
    -0.06
     swirling
    -0.06
    POSITIVE LOGITS
    浼
    0.07
    企业提供
    0.07
     amort
    0.07
    谖
    0.07
    ⇡
    0.06
    传输
    0.06
    >")
    0.06
    곬
    0.06
    פסיכולוג
    0.06
     AAP
    0.06
    Activations Density 0.098%

    No Known Activations