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. 46044
    Prev
    Next
    INDEX
    Explanations

    Code/database snippets

    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
    éªħ
    -0.26
    <Scalar
    -0.26
    æĪIJ为ä¸Ģ个
    -0.24
    ORK
    -0.23
     promin
    -0.23
    bull
    -0.23
    彩ç¥ŀ
    -0.23
    çķĻè¨ĢæĿ¿
    -0.23
    unque
    -0.23
    (Bit
    -0.23
    POSITIVE LOGITS
    åģ¥åº·ç®¡çIJĨ
    0.25
     Profiles
    0.24
    breaking
    0.23
     profiles
    0.23
    Breaking
    0.22
    ervention
    0.22
     Som
    0.22
    è·Ĺ
    0.22
     eds
    0.22
    ÑģÑĤвÑĥ
    0.21
    Activations Density 3.859%

    No Known Activations