© 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. 107662
    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_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
    ç´§ç´§åĽ´ç»ķ
    -0.27
    身穿
    -0.27
    ]){
    -0.26
    翦
    -0.26
    åīª
    -0.26
    ç©¿è¿ĩ
    -0.26
     infr
    -0.25
    龸çİĭ
    -0.24
    ensi
    -0.24
    èĢĮåĩº
    -0.23
    POSITIVE LOGITS
    reste
    0.27
    ece
    0.27
    owan
    0.26
    è¿ĺ好
    0.26
    ivec
    0.26
    dealloc
    0.26
    Wik
    0.25
     Winston
    0.24
    elter
    0.24
    usta
    0.24
    Activations Density 28.358%

    No Known Activations