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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76770
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     lud
    -0.07
    Ẁ
    -0.07
    �
    -0.07
     değ
    -0.07
     Hospital
    -0.07
    veloper
    -0.07
     [{
    -0.07
     Dig
    -0.06
     femme
    -0.06
     الفند
    -0.06
    POSITIVE LOGITS
    保留
    0.08
    اختبار
    0.08
    BarButtonItem
    0.08
    提交
    0.07
    辣椒
    0.07
    的方式
    0.07
    IFICATIONS
    0.07
    circ
    0.07
    汇报
    0.07
    .Cos
    0.07
    Activations Density 0.003%

    No Known Activations