© 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. 11-RESID-POST-AA
    11. 29377
    Prev
    Next
    INDEX
    Explanations

    dangerous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    技术支持
    -0.07
    환경
    -0.07
    !!↵
    -0.07
    佛山市
    -0.07
    )));
↵
    -0.07
    淄博
    -0.07
    财政部
    -0.07
    协会
    -0.07
    税务局
    -0.07
     broker
    -0.07
    POSITIVE LOGITS
    nage
    0.07
     günlük
    0.07
     Ninth
    0.07
     geral
    0.07
     restrained
    0.06
     Böyle
    0.06
     Playoff
    0.06
     образом
    0.06
    _ALARM
    0.06
     Oilers
    0.06
    Activations Density 0.029%

    No Known Activations