© 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. 129461
    Prev
    Next
    INDEX
    Explanations

    web content 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
    宣è¨Ģ
    -0.27
    iore
    -0.26
    bows
    -0.25
    urbed
    -0.24
    èĪį
    -0.24
    nell
    -0.23
    Elf
    -0.23
    Som
    -0.23
    -employed
    -0.23
     Blvd
    -0.23
    POSITIVE LOGITS
    iles
    0.34
    recur
    0.26
    ARGV
    0.25
    æīĭ表
    0.25
     transc
    0.24
    ields
    0.24
    åĪļ
    0.24
    ";//
    0.24
     intric
    0.24
    >//
    0.23
    Activations Density 16.436%

    No Known Activations