© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129242
    Prev
    Next
    INDEX
    Explanations

    can

    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
    Negative Logits
    ä»»ä½ķå½¢å¼ı
    -0.28
    è¦Ĩ
    -0.27
    çݯå¢ĥä¸Ń
    -0.26
    该游æĪı
    -0.26
    æ®ĭçķĻ
    -0.25
    åĦ¿
    -0.25
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.25
     iota
    -0.24
     adam
    -0.24
     Encore
    -0.24
    POSITIVE LOGITS
     timed
    0.28
    æĮ«
    0.27
    åĩıè½»
    0.26
    åij½é¢ĺ
    0.26
     topic
    0.26
    åĵĪå°Ķ
    0.26
    å®ŀäºĭ
    0.25
    tables
    0.25
    bles
    0.25
     initi
    0.25
    Activations Density 19.551%

    No Known Activations