© 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. 64858
    Prev
    Next
    INDEX
    Explanations

    Death

    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
     ÐŁÐ°
    -0.29
     ^=
    -0.26
     somebody
    -0.26
     Disclaimer
    -0.25
    cip
    -0.24
    cies
    -0.24
     charity
    -0.24
    Ep
    -0.24
    uly
    -0.24
     Tutor
    -0.24
    POSITIVE LOGITS
    横
    0.28
    sonian
    0.26
    ç§Ģ
    0.26
    æ©«
    0.26
    çģµæ´»æĢ§
    0.26
     Kut
    0.24
    setLayout
    0.24
    orea
    0.24
    AVE
    0.24
     Valle
    0.24
    Activations Density 14.670%

    No Known Activations