© 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. 91631
    Prev
    Next
    INDEX
    Explanations

    .do

    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
     jóvenes
    -0.07
    ="/"
    -0.07
    вер
    -0.07
     cru
    -0.07
    finalize
    -0.07
     Wellness
    -0.06
    ﴼ
    -0.06
     литер
    -0.06
    شيخ
    -0.06
     Meadows
    -0.06
    POSITIVE LOGITS
    ʬ
    0.08
     cf
    0.07
    家务
    0.07
    饯
    0.07
    支球队
    0.07
    ◦
    0.07
    主义思想
    0.07
    ע
    0.07
     reste
    0.07
    প
    0.06
    Activations Density 0.003%

    No Known Activations