© 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. 129279
    Prev
    Next
    INDEX
    Explanations

    blog/forum excerpts

    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
    è¿Ļ个èģĮä¸ļ
    -0.31
     longest
    -0.29
    cki
    -0.29
    ä¸įåıªæĺ¯
    -0.28
    ãĤ¬ãĤ¤ãĥī
    -0.26
    owler
    -0.26
    anja
    -0.26
    æľĢéļ¾
    -0.26
     tallest
    -0.25
    æľĢéķ¿
    -0.25
    POSITIVE LOGITS
    Certain
    0.26
    ä¸Ģ段æŶéĹ´
    0.25
    ä¸ĢçĤ¹
    0.25
    ishly
    0.25
    çļĦä¸ĢäºĽ
    0.24
    çļĦä¸Ģ款
    0.24
    algo
    0.24
    ÅĤy
    0.24
    #${
    0.23
    xffffffff
    0.23
    Activations Density 44.672%

    No Known Activations