© 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. 88358
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    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
    æİ¥åľ°æ°Ķ
    -0.28
    ç½ijåĿĢ
    -0.26
    æĭĽèģĺä¼ļ
    -0.25
    æĢħ
    -0.25
    建档ç«ĭ
    -0.25
     uniqu
    -0.24
    åIJįæł¡
    -0.24
     nutshell
    -0.24
    ObjectId
    -0.24
    éºŁ
    -0.24
    POSITIVE LOGITS
    isers
    0.29
    /card
    0.26
     coup
    0.26
     required
    0.24
    ÃŃf
    0.24
    åįĥæĸ¹
    0.23
    å°ij
    0.23
     winds
    0.23
    èľī
    0.23
    orum
    0.23
    Activations Density 9.351%

    No Known Activations