Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 46787
    Prev
    Next
    INDEX
    Explanations

    Scientific study of products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olson
    -0.30
     india
    -0.26
    åѦç§ij
    -0.25
    ursive
    -0.25
     indian
    -0.24
     rects
    -0.24
     kenn
    -0.24
    çīº
    -0.24
    ÑģÑĤвенно
    -0.24
    enschaft
    -0.24
    POSITIVE LOGITS
    æĮĤ
    0.28
     Attach
    0.27
    å¾Ĭ
    0.27
    æ´¸
    0.27
    gap
    0.26
    lac
    0.25
    åħ«ä¸ª
    0.25
    åĽ½æľīèµĦ产
    0.25
    äºĭå®ľ
    0.25
    å·¨åŀĭ
    0.24
    Activations Density 0.058%

    No Known Activations