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. 46037
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    otti
    -0.28
    å¼ıçļĦ
    -0.28
    ottom
    -0.27
    æŃ£æĸĩ
    -0.26
     established
    -0.25
    å¼ı
    -0.25
     booths
    -0.25
    letic
    -0.24
    oldt
    -0.24
    isms
    -0.24
    POSITIVE LOGITS
    nic
    0.29
    Ĥ¨
    0.27
    éĵ
    0.27
    unks
    0.25
    animate
    0.25
    梢
    0.25
    åĨįéĢł
    0.24
    urname
    0.24
    ailed
    0.23
    cul
    0.23
    Activations Density 0.862%

    No Known Activations