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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 31387
    Prev
    Next
    INDEX
    Explanations

    technical documentation snippets

    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
    现金流
    -0.07
    Effect
    -0.07
    对标
    -0.07
     Baseball
    -0.07
    	U
    -0.07
    黑马
    -0.07
     microseconds
    -0.07
    增量
    -0.07
     Starbucks
    -0.07
     Horror
    -0.07
    POSITIVE LOGITS
     wishes
    0.07
     modifier
    0.07
    ерт
    0.06
    changes
    0.06
    needle
    0.06
    不断增强
    0.06
    Item
    0.06
    如何
    0.06
    можем
    0.06
    ራ
    0.06
    Activations Density 0.002%

    No Known Activations