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. 23-RESID-POST-AA
    6. 130634
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     정도
    -0.08
    迁移
    -0.07
    IT
    -0.07
    -bound
    -0.07
    .exclude
    -0.07
     Heating
    -0.07
     DNS
    -0.07
    ってしまった
    -0.07
    ycled
    -0.06
    Zip
    -0.06
    POSITIVE LOGITS
    =w
    0.07
    死者
    0.07
    率为
    0.07
     gı
    0.06
     dn
    0.06
     darken
    0.06
     возд
    0.06
    慢性
    0.06
     others
    0.06
     ê
    0.06
    Activations Density 0.094%

    No Known Activations