© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1537
    Prev
    Next
    INDEX
    Explanations

    roman numerals and punctuation

    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
    מוז
    -0.07
    (',')[
    -0.07
    קטע
    -0.07
    !(:
    -0.07
    ros
    -0.07
    蒙古
    -0.07
     fé
    -0.06
    公共资源
    -0.06
    舉辦
    -0.06
    有效性
    -0.06
    POSITIVE LOGITS
    десят
    0.08
     dynam
    0.07
    덟
    0.07
     sy
    0.07
    "><!--
    0.07
     nem
    0.07
    毁
    0.07
     associ
    0.06
    ươi
    0.06
    洗涤
    0.06
    Activations Density 0.023%

    No Known Activations