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. 130995
    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
     greenhouse
    -0.08
    طف
    -0.07
    cedures
    -0.07
    atology
    -0.07
     BRAND
    -0.07
    only
    -0.07
     Foods
    -0.07
    enerating
    -0.07
     accidentally
    -0.07
    了自己的
    -0.07
    POSITIVE LOGITS
     SEC
    0.07
     repression
    0.07
     AA
    0.07
    勰
    0.07
    		  
    0.07
    Ë
    0.07
     (/
    0.06
    Ṁ
    0.06
    )،
    0.06
    ・・・
    0.06
    Activations Density 0.028%

    No Known Activations