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. 72648
    Prev
    Next
    INDEX
    Explanations

    to

    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
    研究中心
    -0.07
    铍
    -0.07
    丰富多彩
    -0.07
    ibNameOrNil
    -0.07
    踏上
    -0.06
     blurry
    -0.06
    吸引了
    -0.06
    شارك
    -0.06
     ayrıca
    -0.06
    ሌ
    -0.06
    POSITIVE LOGITS
    unist
    0.07
     equivalence
    0.07
    Voltage
    0.06
    鳊
    0.06
    泰
    0.06
     Resolve
    0.06
    erta
    0.06
     Eastern
    0.06
     ch
    0.06
    (ticket
    0.06
    Activations Density 0.005%

    No Known Activations