© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71996
    Prev
    Next
    INDEX
    Explanations

    the end-of-user-message delimiter in chat transcripts, especially when the message is a question or request.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
    赛道
    -0.07
     Vs
    -0.07
    致辞
    -0.07
     principals
    -0.07
    .mac
    -0.06
    に対する
    -0.06
    _OID
    -0.06
     �
    -0.06
    _join
    -0.06
    _udp
    -0.06
    POSITIVE LOGITS
    爬上
    0.08
    yscale
    0.07
    哗
    0.07
    纸上
    0.07
    volent
    0.06
    楼下
    0.06
    احتجاج
    0.06
    .EventHandler
    0.06
    农业科技
    0.06
     thwart
    0.06
    Activations Density 0.061%

    No Known Activations