© 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. 77238
    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
    吧
    -0.07
    .HTTP
    -0.07
    שני
    -0.07
    等等
    -0.07
    正好
    -0.07
     vn
    -0.07
    受到
    -0.07
     =================================================
    -0.07
     اسم
    -0.06
    POSITIVE LOGITS
    lar
    0.07
     profitability
    0.07
    היסטוריה
    0.06
    EditingController
    0.06
    鲒
    0.06
     Typically
    0.06
    醮
    0.06
     MAD
    0.06
    👫
    0.06
     decentral
    0.06
    Activations Density 0.001%

    No Known Activations