© 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. 70469
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases where the author speaks in the first person or expresses personal opinion (I, I'm, my, I think, I find, etc.).

    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
    (dateTime
    -0.08
     poems
    -0.07
    牠
    -0.07
    书法家
    -0.07
    宮
    -0.07
    ц
    -0.07
    .TextField
    -0.06
    wealth
    -0.06
    Simon
    -0.06
    _com
    -0.06
    POSITIVE LOGITS
     Lima
    0.08
    党的十
    0.07
    归来
    0.07
     getClient
    0.07
    大的
    0.07
    漫长
    0.07
    回
    0.06
    只要有
    0.06
    ﳇ
    0.06
     sender
    0.06
    Activations Density 0.159%

    No Known Activations