© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 117263
    Prev
    Next
    INDEX
    Explanations

    articles and content licensing

    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
    谔
    -0.07
     Dj
    -0.06
    SOEVER
    -0.06
     течение
    -0.06
    quip
    -0.06
    囹
    -0.06
    깬
    -0.06
    您的
    -0.06
    ﯚ
    -0.06
     înt
    -0.06
    POSITIVE LOGITS
    爸妈
    0.07
    	category
    0.07
     preaching
    0.07
    'Connor
    0.07
    信心
    0.07
     trainers
    0.07
    ADIO
    0.06
    	config
    0.06
    🕛
    0.06
    产值
    0.06
    Activations Density 0.054%

    No Known Activations