© 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. 19-RESID-POST-AA
    11. 7680
    Prev
    Next
    INDEX
    Explanations

    scientific topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Бес
    -0.08
     עשרות
    -0.07
    essenger
    -0.07
     nackt
    -0.07
    すべて
    -0.07
    .Clear
    -0.07
    .accel
    -0.07
     PendingIntent
    -0.07
    genden
    -0.07
     אמנם
    -0.07
    POSITIVE LOGITS
     aid
    0.07
    труд
    0.07
    可愛
    0.07
    Mailer
    0.07
     );↵↵
    0.06
    Uploader
    0.06
    빌
    0.06
     bribery
    0.06
     blocker
    0.06
    !↵↵↵
    0.06
    Activations Density 0.015%

    No Known Activations