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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 36070
    Prev
    Next
    INDEX
    Explanations

    Random snippets of text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \Page
    -0.07
    作为一个
    -0.07
     cosmetic
    -0.07
    如果是
    -0.07
    建成
    -0.07
    ことがあります
    -0.07
    尽可能
    -0.07
    .edu
    -0.06
    南京
    -0.06
    Т
    -0.06
    POSITIVE LOGITS
    special
    0.08
    -storage
    0.07
    �
    0.07
    沈
    0.07
    isers
    0.07
     jspb
    0.07
    ич
    0.07
    安全感
    0.07
     vai
    0.07
     rele
    0.07
    Activations Density 0.007%

    No Known Activations