© 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. 88248
    Prev
    Next
    INDEX
    Explanations

    Memorial

    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
    ecessarily
    -0.28
    æł¸
    -0.27
     Prem
    -0.24
    åĢŁçĶ¨
    -0.24
     NRL
    -0.24
    çŃ¾ç½²
    -0.24
    æĺ¯åIJ¦
    -0.23
    第ä¸Ģ书记
    -0.23
    åįĩèµ·
    -0.23
    ariate
    -0.23
    POSITIVE LOGITS
    管çIJĨåĴĮ
    0.26
    -motion
    0.25
    .native
    0.25
    ãĤ¿ãĤ¤ãĥł
    0.25
    çĭ¬å®¶
    0.24
     tie
    0.24
    èµĦæºIJä¼ĺåĬ¿
    0.24
    owns
    0.24
    \OptionsResolver
    0.24
    antz
    0.24
    Activations Density 9.899%

    No Known Activations