© 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. 60928
    Prev
    Next
    INDEX
    Explanations

    markers that denote the assistant’s turn/role in chat-formatted transcripts (e.g., the assistant header).

    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
    -threat
    -0.07
    én
    -0.07
    *Math
    -0.07
     Stard
    -0.07
    igel
    -0.07
    -connected
    -0.06
    oplayer
    -0.06
    न
    -0.06
    hape
    -0.06
    ;width
    -0.06
    POSITIVE LOGITS
    숭
    0.08
    绅
    0.07
    栗
    0.07
    郊区
    0.07
    胚
    0.07
     brasile
    0.07
     меропри
    0.07
     לפ
    0.07
    ﯜ
    0.07
    钢铁
    0.07
    Activations Density 0.046%

    No Known Activations