© 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. 75288
    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
    ulsion
    -0.07
     longing
    -0.07
     dispenser
    -0.07
    ţi
    -0.07
    ửa
    -0.06
    由
    -0.06
     fixing
    -0.06
    普遍存在
    -0.06
     thermo
    -0.06
    elier
    -0.06
    POSITIVE LOGITS
    .
    0.08
     textbooks
    0.07
    되면
    0.07
     {}↵↵
    0.07
    �
    0.06
     다른
    0.06
    奸
    0.06
    _RS
    0.06
     Davies
    0.06
    Jake
    0.06
    Activations Density 0.462%

    No Known Activations