© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 77326
    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
     captivity
    -0.07
    关键技术
    -0.07
    截至
    -0.07
    .Product
    -0.07
    "},
    -0.06
    _BGR
    -0.06
    个多小时
    -0.06
     Drinking
    -0.06
    作為
    -0.06
     }]
    -0.06
    POSITIVE LOGITS
     interle
    0.08
     loose
    0.07
    骨折
    0.07
     ky
    0.07
     Buffered
    0.07
     MMP
    0.07
     okreś
    0.06
    single
    0.06
     başlat
    0.06
    engu
    0.06
    Activations Density 0.012%

    No Known Activations