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. 130703
    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
    -chief
    -0.08
     Sullivan
    -0.07
     обла
    -0.07
    שנתי
    -0.07
    _fake
    -0.07
    phis
    -0.07
    キャンペーン
    -0.07
    innacle
    -0.07
    upal
    -0.07
     phishing
    -0.07
    POSITIVE LOGITS
     #
    0.08
    kbd
    0.07
    铊
    0.07
     gem
    0.07
     //
    0.07
    信赖
    0.07
     time
    0.07
     takes
    0.07
     Ч
    0.07
     draw
    0.07
    Activations Density 0.026%

    No Known Activations