© 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. 86726
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    脱落
    -0.07
    实践经验
    -0.06
    作坊
    -0.06
    可以帮助
    -0.06
    vil
    -0.06
    赋能
    -0.06
    mie
    -0.06
    年龄段
    -0.06
    เผยแ
    -0.06
    问问
    -0.06
    POSITIVE LOGITS
    (SYS
    0.08
     STAT
    0.07
    .annotate
    0.07
    ients
    0.07
     mặt
    0.07
    開啟
    0.07
     OLED
    0.07
     płyt
    0.07
    ',
↵
    0.06
     �
    0.06
    Activations Density 0.026%

    No Known Activations