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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88090
    Prev
    Next
    INDEX
    Explanations

    tax-exempt status

    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
    ="\
    -0.07
    臑
    -0.07
    奖励
    -0.07
    .Bar
    -0.07
    .ar
    -0.06
     Product
    -0.06
    .ResponseWriter
    -0.06
    幂
    -0.06
    мя
    -0.06
    _upper
    -0.06
    POSITIVE LOGITS
    妨
    0.07
    acie
    0.07
     proced
    0.07
     lesbienne
    0.07
     soccer
    0.07
    _soup
    0.07
     iframe
    0.06
     מקום
    0.06
    쑈
    0.06
    オー
    0.06
    Activations Density 0.036%

    No Known Activations