© 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. 107565
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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
    astic
    -0.29
    ç»ıèIJ¥æ´»åĬ¨
    -0.27
    人æŃ»äº¡
    -0.27
    astics
    -0.27
    igrated
    -0.25
     arrang
    -0.24
    reu
    -0.24
    PPER
    -0.24
    裾
    -0.24
    UNET
    -0.24
    POSITIVE LOGITS
    鼶
    0.31
    æķ´
    0.31
     zero
    0.29
     stagn
    0.27
    å¸ĥ
    0.26
     bid
    0.26
    Bid
    0.25
    ç½ij讯
    0.24
     sorts
    0.24
    arp
    0.24
    Activations Density 21.126%

    No Known Activations