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. 46413
    Prev
    Next
    INDEX
    Explanations

    Gun

    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
     ech
    -0.28
    æľ¬ä¹¦
    -0.27
    move
    -0.27
    zer
    -0.27
    .rawValue
    -0.26
     bu
    -0.26
    NET
    -0.24
    å¼ĢæĪ·
    -0.24
     cru
    -0.24
    ä¿ĥè¿ĽäºĨ
    -0.24
    POSITIVE LOGITS
    igy
    0.27
    sst
    0.27
    æĹ¥äº§
    0.26
     royalty
    0.25
     Hitch
    0.25
    trag
    0.25
     GB
    0.25
    åĴ¬
    0.24
     Finder
    0.24
    å¾ģæ±ĤæĦıè§ģ
    0.24
    Activations Density 0.013%

    No Known Activations