© 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. 5970
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    æĿ¡æ¬¾
    -0.30
    åħĥç´ł
    -0.28
    _clause
    -0.27
    æĥ¦
    -0.26
    æĥ³èµ·æĿ¥
    -0.26
     Elements
    -0.26
    ãĤ¢ãĤ¯
    -0.26
     cá»Ń
    -0.25
    éłģ
    -0.25
    è¿Ļéĥ¨åĪĨ
    -0.25
    POSITIVE LOGITS
    undle
    0.29
    两次
    0.27
    lesi
    0.27
     holds
    0.26
     demos
    0.26
    åı¬å¼Ģ
    0.25
     nämlich
    0.25
     auxiliary
    0.25
     holding
    0.25
    两大
    0.25
    Activations Density 0.019%

    No Known Activations