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. 109847
    Prev
    Next
    INDEX
    Explanations

    code parameters

    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
    gesch
    -0.08
    缯
    -0.07
    FontSize
    -0.07
    findAll
    -0.07
    קני
    -0.07
     boast
    -0.07
    .AspNet
    -0.07
    日常生活
    -0.07
     cushions
    -0.07
    的最后一
    -0.07
    POSITIVE LOGITS
    ?↵
    0.07
     RUN
    0.07
    做了
    0.06
    $config
    0.06
    。”
    0.06
    _nh
    0.06
     tolerate
    0.06
    ,…
    0.06
    依據
    0.06
    执着
    0.06
    Activations Density 0.008%

    No Known Activations