© 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. 62978
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ãģĮãĤī
    -0.28
    ãĥªãĥ³ãĤ¯
    -0.27
    ç³»ç»ŁçļĦ
    -0.26
    éĥ½å·²ç»ı
    -0.26
     grip
    -0.26
    æĺİæĺİ
    -0.25
     só
    -0.24
    åĬŀåħ¬å®¤
    -0.24
    lob
    -0.24
    ubbles
    -0.24
    POSITIVE LOGITS
    exe
    0.26
    allas
    0.26
    åĵºä¹³
    0.25
    ServiceProvider
    0.25
    ç¿»
    0.24
    -wise
    0.24
    éĢļçķħ
    0.24
    ãĤ³ãĥ¼ãĥ
    0.24
    æĭ¾
    0.24
    æĸ¹ä¾¿
    0.23
    Activations Density 1.048%

    No Known Activations

    This feature has no known activations.