Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 75775
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engulf
    -0.07
     draws
    -0.07
    新西兰
    -0.07
     keto
    -0.07
     enquanto
    -0.07
    扎
    -0.07
    .map
    -0.07
     çekil
    -0.07
    ymm
    -0.07
    ază
    -0.06
    POSITIVE LOGITS
    制度改革
    0.07
    itude
    0.07
     нашего
    0.07
    ≠
    0.07
    国家级
    0.07
     первого
    0.07
    ический
    0.06
     جدا
    0.06
    �
    0.06
    差距
    0.06
    Activations Density 0.123%

    No Known Activations