© 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. 5860
    Prev
    Next
    INDEX
    Explanations

    .

    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
    æīĢè°ĵçļĦ
    -0.31
    æľīæĿ¡ä»¶çļĦ
    -0.26
     Guardian
    -0.24
    æĽ´å¤ļçļĦ
    -0.24
    è¿ĻäºĽä¸ľè¥¿
    -0.24
    ese
    -0.23
    <typeof
    -0.23
    æľĢå¤ļçļĦ
    -0.23
    {{{
    -0.23
    è¿ĺä¸įæĺ¯
    -0.23
    POSITIVE LOGITS
    AGIC
    0.27
    亮
    0.24
     ;↵↵↵
    0.24
    ään
    0.24
     azi
    0.24
    第ä¸ĢæĿ¡
    0.24
    regex
    0.24
    -License
    0.23
    rez
    0.23
    å°¼æĸ¯
    0.23
    Activations Density 0.045%

    No Known Activations