© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 127482
    Prev
    Next
    INDEX
    Explanations

    phere

    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
    (||
    -0.07
    Ƥ
    -0.07
     pounded
    -0.07
    ุด
    -0.06
    裁
    -0.06
    western
    -0.06
    So
    -0.06
     Chip
    -0.06
    pig
    -0.06
    quo
    -0.06
    POSITIVE LOGITS
    限购
    0.08
     Lumia
    0.08
     predatory
    0.07
     lear
    0.07
    于是我
    0.07
     Sistema
    0.07
    蛞
    0.07
    relations
    0.07
    電子郵件
    0.07
     לח
    0.06
    Activations Density 0.001%

    No Known Activations