© 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. 23-RESID-POST-AA
    11. 483
    Prev
    Next
    INDEX
    Explanations

    Chinese history and warfare

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     callback
    -0.08
    原告
    -0.07
    王先生
    -0.07
     הש
    -0.07
     реш
    -0.06
    حاد
    -0.06
    商场
    -0.06
     addCriterion
    -0.06
    soap
    -0.06
    奇迹
    -0.06
    POSITIVE LOGITS
     chế
    0.08
    ально
    0.07
     virtually
    0.07
     Tactical
    0.07
     sẽ
    0.07
     Fleet
    0.07
    -key
    0.07
    atk
    0.06
    眼部
    0.06
     Het
    0.06
    Activations Density 0.018%

    No Known Activations