© 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 EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 128298
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron detects the second-person pronoun "you" when the user addresses or asks the assistant directly (user-directed questions/requests).

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    מעט
    -0.07
     cut
    -0.07
    anto
    -0.07
    兑现
    -0.06
    国情
    -0.06
    .gridy
    -0.06
    合金
    -0.06
    𝐗
    -0.06
    肥胖
    -0.06
    歐
    -0.06
    POSITIVE LOGITS
     serving
    0.08
     risult
    0.07
     proyecto
    0.07
    =create
    0.07
    _traits
    0.07
     données
    0.07
    日の
    0.07
    _src
    0.07
     cré
    0.07
     diaper
    0.07
    Activations Density 0.062%

    No Known Activations