© 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. 107418
    Prev
    Next
    INDEX
    Explanations

    Code and web content

    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
     zwy
    -0.31
    shade
    -0.27
     profil
    -0.26
    æ³Ħ
    -0.26
     dumps
    -0.26
    ÙĬاÙĨ
    -0.25
     solely
    -0.25
    å¿ĺ
    -0.25
     vg
    -0.25
     purely
    -0.24
    POSITIVE LOGITS
    -framework
    0.29
     Us
    0.28
    å¸Ĥå§Ķ常å§Ķ
    0.25
    .chapter
    0.25
    atility
    0.24
    à¸Ĥà¸Ļ
    0.24
    åĩłå®¶
    0.24
    人æ°ijåĮ»éĻ¢
    0.24
     us
    0.23
    p
    0.23
    Activations Density 66.333%

    No Known Activations