© 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. 75512
    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
     Bernard
    -0.07
     reform
    -0.07
    amine
    -0.07
    墨西哥
    -0.07
     cog
    -0.07
    .non
    -0.07
     Reed
    -0.07
    裁
    -0.07
    �재
    -0.07
    Automatic
    -0.07
    POSITIVE LOGITS
     UIAlertView
    0.07
    抖音
    0.07
    煋
    0.07
    텡
    0.07
     outlook
    0.07
    thèque
    0.06
    뎀
    0.06
    딮
    0.06
    怎么做
    0.06
     setters
    0.06
    Activations Density 0.013%

    No Known Activations