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. 2-TRANSCODER-HP
    4. 106
    Prev
    Next
    INDEX
    Explanations

    -ified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_2.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.2.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izont
    -0.27
    ationally
    -0.27
    ç«Ļéķ¿
    -0.26
    itti
    -0.25
     skal
    -0.25
    AndView
    -0.25
    itionally
    -0.24
    ÑĮе
    -0.24
    	cursor
    -0.24
    æ°´å¹³
    -0.24
    POSITIVE LOGITS
    æīĵå¾Ĺ
    0.26
    queues
    0.26
     buffered
    0.25
    硬
    0.24
     dign
    0.24
    ãģ¾ãģĦ
    0.24
    顺
    0.24
    reverse
    0.24
     spec
    0.24
    è¿ij代
    0.24
    Activations Density 28.131%

    No Known Activations