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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 59643
    Prev
    Next
    INDEX
    Explanations

    code/technical specifications

    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
     railways
    -0.08
     cited
    -0.07
    彖
    -0.07
    .Atoi
    -0.07
    Ⲟ
    -0.07
     Browns
    -0.07
     Plains
    -0.07
    镴
    -0.06
    吝
    -0.06
     Prom
    -0.06
    POSITIVE LOGITS
    ResponseType
    0.07
    根底
    0.06
     OBJECT
    0.06
     màn
    0.06
    万辆
    0.06
    身影
    0.06
    .rect
    0.06
     Zh
    0.06
    قيقة
    0.06
    عودة
    0.06
    Activations Density 0.124%

    No Known Activations