© 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. 80719
    Prev
    Next
    INDEX
    Explanations

    Ju

    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
     spre
    -0.08
     aa
    -0.08
     Quentin
    -0.08
     sera
    -0.07
    跟他
    -0.07
     très
    -0.07
    あり
    -0.07
    特斯
    -0.07
    條
    -0.07
    (Double
    -0.07
    POSITIVE LOGITS
    的关键
    0.07
     orchestrated
    0.07
     choisir
    0.07
    有机结合
    0.07
    שב
    0.07
    的发生
    0.06
    寫
    0.06
     getSystemService
    0.06
    Maker
    0.06
    推崇
    0.06
    Activations Density 0.006%

    No Known Activations