© 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. 7-RESID-POST-AA
    11. 80436
    Prev
    Next
    INDEX
    Explanations

    Drosophila

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     najczęście
    -0.08
     cough
    -0.07
    _rooms
    -0.07
     colour
    -0.07
     paginate
    -0.07
    Roll
    -0.07
    rippling
    -0.07
    .LENGTH
    -0.07
    ชำระ
    -0.07
    Ƥ
    -0.06
    POSITIVE LOGITS
     Eu
    0.07
     אני
    0.07
    生活习惯
    0.07
    했던
    0.07
    탔
    0.07
    容器
    0.07
     Hil
    0.07
     Aaron
    0.07
     Mia
    0.07
    把它
    0.07
    Activations Density 0.002%

    No Known Activations