© 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
    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. 29596
    Prev
    Next
    INDEX
    Explanations

    Chinese language

    np_max-act · gemini-2.0-flash
    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
    ရ
    -0.07
    classification
    -0.07
    ව
    -0.07
     childbirth
    -0.06
    _go
    -0.06
    在一
    -0.06
     authorization
    -0.06
    _interaction
    -0.06
    تشغيل
    -0.06
    工作岗位
    -0.06
    POSITIVE LOGITS
    霸
    0.07
    مؤ
    0.07
    ombine
    0.07
    三位
    0.06
    alie
    0.06
    uede
    0.06
    inction
    0.06
     konnte
    0.06
    Ḵ
    0.06
     אישי
    0.06
    Activations Density 0.072%

    No Known Activations