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. 7190
    Prev
    Next
    INDEX
    Explanations

    :

    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
    柃
    -0.07
    帮你
    -0.07
    alties
    -0.07
     Michele
    -0.07
     sealed
    -0.07
    棠
    -0.06
    油耗
    -0.06
    깥
    -0.06
    命中
    -0.06
    _Impl
    -0.06
    POSITIVE LOGITS
    自在
    0.08
    不是
    0.07
    それぞれ
    0.07
    -other
    0.07
    嫔
    0.07
    神经系统
    0.07
     →↵↵
    0.06
    扎实推进
    0.06
     ghetto
    0.06
     organising
    0.06
    Activations Density 0.008%

    No Known Activations