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. 130959
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    activities
    -0.08
     visita
    -0.08
    有哪些
    -0.07
     טי
    -0.07
    咸阳
    -0.07
    חי
    -0.07
     youthful
    -0.07
     dann
    -0.07
    ▿
    -0.07
    ampilkan
    -0.07
    POSITIVE LOGITS
    移到
    0.07
     Death
    0.07
     #
    0.07
    компонент
    0.06
    模特
    0.06
    String
    0.06
    شهد
    0.06
     World
    0.06
     Device
    0.06
    入睡
    0.06
    Activations Density 0.022%

    No Known Activations