© 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. 141755
    Prev
    Next
    INDEX
    Explanations

    Code/document snippets

    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
    eve
    -0.29
    rice
    -0.26
    éģĹæĨ¾
    -0.25
     hose
    -0.24
    æ¼ĶåĮĸ
    -0.24
    åŁ¹åħ»
    -0.24
    airs
    -0.24
    è¯Ńè¨Ģ
    -0.23
    .getInteger
    -0.23
     esi
    -0.23
    POSITIVE LOGITS
     suppl
    0.27
    æķĮ
    0.27
    ancellation
    0.26
    æĥ³åĪ°
    0.25
    DEX
    0.25
     Ñģмог
    0.25
    /stretchr
    0.24
     Bas
    0.24
    ç§ijæĬĢ大åѦ
    0.24
    xab
    0.23
    Activations Density 8.785%

    No Known Activations