© 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. 42576
    Prev
    Next
    INDEX
    Explanations

    J

    np_max-act · gemini-2.0-flash
    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
     precisely
    -0.07
    真实性
    -0.07
     vị
    -0.07
     ansible
    -0.06
     dello
    -0.06
    秦
    -0.06
    寇
    -0.06
    /component
    -0.06
    	case
    -0.06
     typeof
    -0.06
    POSITIVE LOGITS
     slashes
    0.08
    继续保持
    0.07
    Plain
    0.07
    🗞
    0.07
    owment
    0.07
     accumulating
    0.07
    świ
    0.07
    公寓
    0.07
    شاه
    0.07
    ();}↵
    0.07
    Activations Density 0.005%

    No Known Activations