© 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. 76630
    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
    すると
    -0.07
     blanc
    -0.07
     AssemblyTrademark
    -0.07
    ञ
    -0.07
    anh
    -0.06
    "is
    -0.06
     hopeful
    -0.06
     sat
    -0.06
    检
    -0.06
    勘探
    -0.06
    POSITIVE LOGITS
    数码
    0.08
    Todos
    0.07
    퀵
    0.07
    SETTINGS
    0.07
    ibName
    0.07
     vatanda
    0.07
     проб
    0.07
    虚拟
    0.07
    ArrayList
    0.07
     authenticated
    0.07
    Activations Density 0.100%

    No Known Activations