© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89947
    Prev
    Next
    INDEX
    Explanations

    code

    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
    内部控制
    -0.08
    .getTarget
    -0.08
    创建工作
    -0.07
     yans
    -0.07
    uvw
    -0.07
    销毁
    -0.07
     القوم
    -0.07
    -upper
    -0.07
     plumber
    -0.07
     allocated
    -0.07
    POSITIVE LOGITS
    'in
    0.08
    Cons
    0.08
    (out
    0.07
    廳
    0.07
     ([
    0.07
    Out
    0.07
           ↵↵
    0.07
                  ↵
    0.07
    -Benz
    0.06
    	not
    0.06
    Activations Density 0.024%

    No Known Activations