© 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. 23-TRANSCODER-HP
    7. 162594
    Prev
    Next
    INDEX
    Explanations

    Code and mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢĤï¼Ī
    -0.29
    ertain
    -0.26
    ä¹ŁæŃ£æĺ¯
    -0.26
    ãĢĤ↵↵
    -0.26
    agra
    -0.25
    antly
    -0.24
    æķĻèĤ²åŁ¹è®Ń
    -0.23
    ä¸ĭæ»ij
    -0.23
    æľĢ好
    -0.23
    ç¼ĸè¾ij
    -0.23
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀ
    0.42
     what
    0.38
    为ä»Ģä¹Īä¼ļ
    0.35
    为ä»Ģä¹Īè¦ģ
    0.35
    请éĹ®
    0.34
     why
    0.34
    ä»Ģä¹Īæĺ¯
    0.33
    ä»Ģä¹Īåı«
    0.33
     whats
    0.32
     What
    0.32
    Activations Density 0.019%

    No Known Activations