Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 25701
    Prev
    Next
    INDEX
    Explanations

    syndicated columnists

    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
    IPPING
    -0.07
    ��
    -0.07
    点了点头
    -0.07
     unfairly
    -0.07
    翌
    -0.07
    \"></
    -0.07
    🉑
    -0.07
     Relief
    -0.07
    /slick
    -0.07
    要好好
    -0.07
    POSITIVE LOGITS
     meisten
    0.08
    bot
    0.07
    �
    0.07
    _connection
    0.07
    私の
    0.06
    url
    0.06
    atter
    0.06
    otine
    0.06
    /Object
    0.06
    そもそも
    0.06
    Activations Density 0.005%

    No Known Activations