© 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. 64859
    Prev
    Next
    INDEX
    Explanations

    detects tokens that signal existence or introduce a list of items (lead‑ins to enumerations).

    oai_token-act-pair · gpt-5-miniTriggered 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
    瀛
    -0.07
    -num
    -0.07
    Pop
    -0.06
    rotein
    -0.06
     граждан
    -0.06
     door
    -0.06
     дерев
    -0.06
     bruises
    -0.06
    aban
    -0.06
     Portug
    -0.06
    POSITIVE LOGITS
    美学
    0.07
     opt
    0.07
    堆
    0.06
    岁时
    0.06
    ספט
    0.06
     simply
    0.06
    _DEF
    0.06
    	base
    0.06
    奥
    0.06
    焚烧
    0.06
    Activations Density 0.505%

    No Known Activations