© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41803
    Prev
    Next
    INDEX
    Explanations

    subjects

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嗳
    -0.07
    "]}
    -0.07
    Sw
    -0.07
     Cr
    -0.07
    忍
    -0.07
     Plaintiff
    -0.07
     resolution
    -0.07
    InputStream
    -0.06
    犯
    -0.06
    降
    -0.06
    POSITIVE LOGITS
    ı
    0.07
    .tem
    0.07
    也算
    0.07
    اجتماع
    0.07
    뮈
    0.07
     Пет
    0.07
    되었
    0.07
    _CELL
    0.07
    luğun
    0.07
    ESİ
    0.06
    Activations Density 0.140%

    No Known Activations