© 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. 108157
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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
    ,class
    -0.25
     preceded
    -0.25
     Lau
    -0.25
    åĨĹ
    -0.24
    akov
    -0.24
     PIXEL
    -0.24
    Ļ¨
    -0.24
    /question
    -0.23
     understands
    -0.23
    çļĦéĤ£ä¸Ģ
    -0.23
    POSITIVE LOGITS
    æ´½
    0.28
    æĮĸæİĺ
    0.28
     ged
    0.27
    éĵĽ
    0.25
     magn
    0.25
     but
    0.25
    [file
    0.25
     wound
    0.24
     dumped
    0.24
    but
    0.23
    Activations Density 14.376%

    No Known Activations