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. 15-RESID-POST-AA
    6. 78024
    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_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
     */↵↵↵
    -0.07
    stre
    -0.07
     rose
    -0.07
     ngân
    -0.07
    "T
    -0.06
    	            
    -0.06
     encouraged
    -0.06
     thẻ
    -0.06
     Ezek
    -0.06
    .getDeclared
    -0.06
    POSITIVE LOGITS
    全球最大
    0.07
     cancellation
    0.07
     replacement
    0.06
     yayınlan
    0.06
     מדהים
    0.06
    的理想
    0.06
    .frequency
    0.06
    -lasting
    0.06
    丰满
    0.06
    롄
    0.06
    Activations Density 0.015%

    No Known Activations