© 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. 77981
    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
    邓小平
    -0.07
     Tasmania
    -0.07
    ouv
    -0.07
    áz
    -0.07
    ក
    -0.07
    充值
    -0.07
     Ngoài
    -0.06
     københavn
    -0.06
    影视
    -0.06
     Lions
    -0.06
    POSITIVE LOGITS
     registry
    0.07
    _icall
    0.07
     instructors
    0.07
     inference
    0.07
    -sale
    0.06
    经济增长
    0.06
    üssen
    0.06
    trag
    0.06
     ILogger
    0.06
    롑
    0.06
    Activations Density 0.002%

    No Known Activations