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

    Neuronpedia

    APICircuit 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. 129458
    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
    SCRIBE
    -0.08
    手势
    -0.07
    setPosition
    -0.07
    一览
    -0.06
     Wagner
    -0.06
     handleMessage
    -0.06
     ARM
    -0.06
    -layout
    -0.06
     waved
    -0.06
     Sweep
    -0.06
    POSITIVE LOGITS
    ****↵
    0.07
    fund
    0.07
    湘
    0.07
     serum
    0.07
    贵州省
    0.07
    粉
    0.07
     Total
    0.07
    庵
    0.06
       ↵    ↵
    0.06
    ,model
    0.06
    Activations Density 0.011%

    No Known Activations