© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5732
    Prev
    Next
    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¦ĸå¯Į
    -0.29
     everything
    -0.26
    æı®
    -0.25
    é¼¾
    -0.25
     hWnd
    -0.24
    è¿ĺæĥ³
    -0.24
    æĮĤ
    -0.24
    everything
    -0.24
    ncoder
    -0.24
    -depth
    -0.23
    POSITIVE LOGITS
    Ļ¨
    0.27
    æĥħ
    0.26
    çļĦæĦıè§ģ
    0.24
    iju
    0.24
    edy
    0.24
    imas
    0.24
    Fed
    0.24
    缦
    0.23
    çļĦæĥħ
    0.23
     im
    0.23
    Activations Density 0.017%

    No Known Activations