© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 49375
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    the special chat-format tokens that mark the start (and sometimes end) of an assistant message or turn boundaries.

    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
     gerçekten
    -0.08
     legitimately
    -0.07
    _domains
    -0.07
    けば
    -0.07
    就算
    -0.07
     Cult
    -0.07
    IgnoreCase
    -0.07
    قيقي
    -0.07
    大人
    -0.07
     servi
    -0.06
    POSITIVE LOGITS
    爆炸
    0.07
    (dst
    0.07
    tearDown
    0.07
     dma
    0.07
    mandatory
    0.07
    ♟
    0.07
     crash
    0.07
    并发
    0.07
     loading
    0.06
    退出
    0.06
    Activations Density 0.133%

    No Known Activations