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. 72497
    Prev
    Next
    INDEX
    Explanations

    parenthesis "("

    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
    .GetCurrentMethod
    -0.08
     Notre
    -0.07
     tune
    -0.06
    adjusted
    -0.06
     Meal
    -0.06
    董事
    -0.06
    させて
    -0.06
     currentDate
    -0.06
    哆
    -0.06
    艚
    -0.06
    POSITIVE LOGITS
     новых
    0.07
     sprawling
    0.07
     surrounds
    0.07
    =logging
    0.07
     supremacy
    0.07
    チェ
    0.06
    ORG
    0.06
     FPGA
    0.06
    рупп
    0.06
    滚动
    0.06
    Activations Density 0.016%

    No Known Activations