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. 87936
    Prev
    Next
    INDEX
    Explanations

    receiving

    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
     Gil
    -0.08
     withhold
    -0.07
    $this
    -0.07
    ivre
    -0.07
    इ
    -0.07
    兹
    -0.07
    �
    -0.07
    布朗
    -0.07
     Вот
    -0.07
    .Is
    -0.06
    POSITIVE LOGITS
    ":["
    0.08
    (rx
    0.07
    impact
    0.07
    autoplay
    0.07
    促进了
    0.07
     stint
    0.06
    峰值
    0.06
    быт
    0.06
     cruise
    0.06
    尽管
    0.06
    Activations Density 0.020%

    No Known Activations