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. 11-RESID-POST-AA
    6. 25873
    Prev
    Next
    INDEX
    Explanations

    level

    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
    泽连
    -0.08
     �
    -0.08
    澼
    -0.07
     processData
    -0.07
    萋
    -0.07
    pożycz
    -0.07
     contrasts
    -0.07
    垸
    -0.07
    VisualStyle
    -0.07
    ╴
    -0.06
    POSITIVE LOGITS
     crude
    0.08
    Dec
    0.07
    图片
    0.07
    地位
    0.07
     marque
    0.07
     Coupe
    0.07
    人民医院
    0.07
     Identification
    0.07
    创造
    0.07
    _Dec
    0.07
    Activations Density 0.004%

    No Known Activations