© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107836
    Prev
    Next
    INDEX
    Explanations

    Technology and finance

    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
    Not in Any Lists

    No Comments

    Negative Logits
    西çıŃ
    -0.28
    ayload
    -0.27
    åıĪ好
    -0.26
    multip
    -0.25
     vá
    -0.25
    翳
    -0.24
    ï¼µ
    -0.24
     seria
    -0.24
    å°±æĺ¯ä¸ºäºĨ
    -0.24
    åıĹä¼Ĺ
    -0.24
    POSITIVE LOGITS
    å¥ĩå¼Ĥ
    0.28
    åĪĽéĢł
    0.27
    åīµéĢł
    0.25
    ooth
    0.24
    ("${
    0.24
    ÅĪ
    0.24
    åį¿
    0.24
     Engel
    0.23
     Squadron
    0.23
    æľĢæľī
    0.23
    Activations Density 23.241%

    No Known Activations