© 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. 27-TRANSCODER-HP
    7. 7886
    Prev
    Next
    INDEX
    Explanations

    documents with numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    CURRENT
    -0.26
    circ
    -0.26
    Wrapped
    -0.24
    ãĥªãĥ³ãĤ°
    -0.24
     vessel
    -0.24
    arias
    -0.24
    å¹³åı°ä¸Ĭ
    -0.24
    -less
    -0.23
    (comb
    -0.23
    æĺİæĹ¥
    -0.23
    POSITIVE LOGITS
     Fre
    0.31
    annon
    0.26
    loe
    0.26
    ç²Ĵ
    0.24
    ongyang
    0.24
    对å¾ħ
    0.24
    讨
    0.24
     macro
    0.24
    åĸľ
    0.24
    ctal
    0.23
    Activations Density 0.008%

    No Known Activations