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. 88134
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    时代中国
    -0.07
    �
    -0.07
    חדש
    -0.07
    &p
    -0.07
     Featured
    -0.07
     INCLUDED
    -0.07
     �
    -0.07
    ᠢ
    -0.07
    .↵↵↵↵↵↵↵↵↵↵
    -0.07
    꿈
    -0.07
    POSITIVE LOGITS
    ography
    0.09
     الاجتماعية
    0.08
     paragraphs
    0.07
    手段
    0.07
     XPath
    0.07
     보
    0.07
    (parser
    0.07
    流域
    0.07
    PATH
    0.07
    /project
    0.07
    Activations Density 0.012%

    No Known Activations