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. 2300
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    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
    .Scene
    -0.07
    𝄱
    -0.07
    сли
    -0.07
     Redistribution
    -0.06
    oupon
    -0.06
     QB
    -0.06
    =D
    -0.06
     NOTICE
    -0.06
    一季度
    -0.06
     كنت
    -0.06
    POSITIVE LOGITS
    痪
    0.07
    тов
    0.07
     geçen
    0.07
    .feedback
    0.07
    TEMPLATE
    0.07
    -tracking
    0.07
     ander
    0.07
     oe
    0.07
    writer
    0.06
     refusal
    0.06
    Activations Density 0.087%

    No Known Activations