© 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. 15-RESID-POST-AA
    11. 52763
    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
    女子
    -0.07
    (ind
    -0.07
    🚇
    -0.07
    _j
    -0.07
    ヲ
    -0.07
     Р
    -0.07
    duğunu
    -0.07
     />";↵
    -0.07
    ätig
    -0.07
    点儿
    -0.06
    POSITIVE LOGITS
    扩建
    0.07
     Secret
    0.07
    fell
    0.07
    [file
    0.06
    uil
    0.06
    不合理
    0.06
     واست
    0.06
    pile
    0.06
    ساهم
    0.06
    购置
    0.06
    Activations Density 0.146%

    No Known Activations