© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 42270
    Prev
    Next
    INDEX
    Explanations

    0

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JO
    -0.08
    long
    -0.07
    ảnh
    -0.07
     !(
    -0.07
    ’y
    -0.07
    均匀
    -0.07
    美丽
    -0.07
    畅
    -0.07
    的感受
    -0.07
    咏
    -0.07
    POSITIVE LOGITS
     Typeface
    0.07
     tapped
    0.07
     Known
    0.07
    qualified
    0.07
     Experts
    0.06
     kidnapped
    0.06
     trainers
    0.06
     kt
    0.06
    被抓
    0.06
    _Print
    0.06
    Activations Density 0.023%

    No Known Activations