© 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. 22707
    Prev
    Next
    INDEX
    Explanations

    ball sports

    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
    periences
    -0.08
    坐落在
    -0.08
     JAXB
    -0.07
    ឆ
    -0.07
    (Page
    -0.07
     │
    -0.07
    şeh
    -0.07
    مجموع
    -0.07
    _CB
    -0.07
    蔫
    -0.07
    POSITIVE LOGITS
    contra
    0.07
    大量
    0.07
     bol
    0.07
     asian
    0.07
     han
    0.07
    异常
    0.07
     hizo
    0.07
    いら
    0.06
     util
    0.06
    _email
    0.06
    Activations Density 0.013%

    No Known Activations