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. 36329
    Prev
    Next
    INDEX
    Explanations

    code

    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
    تحميل
    -0.07
     mus
    -0.07
    :↵
    -0.07
     draw
    -0.07
    勉强
    -0.07
    ὑ
    -0.06
    ORIZONTAL
    -0.06
    .vol
    -0.06
    _logging
    -0.06
    POSITIVE LOGITS
     }));↵↵
    0.07
    抑制
    0.07
    案
    0.07
    动力电池
    0.07
    )":
    0.07
    等活动
    0.07
    unci
    0.07
    냈
    0.06
    这一
    0.06
    采摘
    0.06
    Activations Density 0.114%

    No Known Activations