© 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. 18-TRANSCODER-HP
    7. 90165
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ·¨
    -0.28
    æĹłåĬĽ
    -0.27
    ç«ĭåĪ»
    -0.26
    æ¯ģ
    -0.26
     defeat
    -0.26
    fs
    -0.26
    æŁ¥
    -0.26
    å®ģåİ¿
    -0.25
    å¸Ĥåľºè§Ħ模
    -0.24
     markdown
    -0.24
    POSITIVE LOGITS
    arness
    0.27
    ennial
    0.27
    enty
    0.26
     ostat
    0.26
     extradition
    0.26
     indoors
    0.26
    ennie
    0.26
    heim
    0.26
    encial
    0.25
    æĢ»éĩı
    0.25
    Activations Density 11.118%

    No Known Activations