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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 75653
    Prev
    Next
    INDEX
    Explanations

    political terms and elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发行人
    -0.08
     Package
    -0.07
    Encrypt
    -0.07
    检察
    -0.07
    jury
    -0.07
    ickers
    -0.07
     fulfill
    -0.07
    KindOfClass
    -0.07
     Protect
    -0.07
     השק
    -0.07
    POSITIVE LOGITS
    されました
    0.07
    استفادة
    0.07
    אווירה
    0.06
    てきて
    0.06
    .startDate
    0.06
    ⊹
    0.06
    _aw
    0.06
     jour
    0.06
    괼
    0.06
     ad
    0.06
    Activations Density 0.037%

    No Known Activations