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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141235
    Prev
    Next
    INDEX
    Explanations

    Common language structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    好ä¸į容æĺĵ
    -0.42
    å°±æĺ¯ä¸ºäºĨ
    -0.36
    æĺ¯ä¸ºäºĨ
    -0.34
    é¢Ŀå¤ĸ
    -0.32
    çļĦåĬªåĬĽ
    -0.32
    è²»
    -0.31
    åıªæĺ¯ä¸ºäºĨ
    -0.31
    è¾Ľèĭ¦
    -0.30
     sacrificed
    -0.30
    è´¹
    -0.30
    POSITIVE LOGITS
     “
    0.28
    çĶ»åĥı
    0.27
    iÄį
    0.27
     (“
    0.25
     "
    0.25
     without
    0.25
    æĹłéļľç¢į
    0.24
    缺å°ij
    0.24
    es
    0.24
    ↵
    0.24
    Activations Density 59.980%

    No Known Activations