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. 46801
    Prev
    Next
    INDEX
    Explanations

    color

    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
    ä»»
    -0.30
     Trust
    -0.29
    责任åζ
    -0.29
    Trust
    -0.27
     versa
    -0.27
     HMS
    -0.27
    ä¿¡ä»»
    -0.26
     Trustees
    -0.26
    æĥ³åΰ
    -0.26
    habi
    -0.25
    POSITIVE LOGITS
     color
    0.26
    sil
    0.26
    åĮĸåIJĪ
    0.26
     materia
    0.25
    ç´łé£Ł
    0.25
     Ready
    0.25
    .SIG
    0.25
    çļĦæķ´ä½ĵ
    0.24
    è¨Ģ
    0.24
     tslint
    0.24
    Activations Density 0.067%

    No Known Activations