© 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. 63311
    Prev
    Next
    INDEX
    Explanations

    Code, dates, or references

    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
    ahi
    -0.27
    ndon
    -0.25
     borrowed
    -0.25
    Expansion
    -0.25
    zzle
    -0.25
    廳
    -0.24
    ilinx
    -0.24
     Silver
    -0.24
     silver
    -0.24
    å¹Ħ
    -0.24
    POSITIVE LOGITS
    æĹ©
    0.29
    éĺ´éĺ³
    0.28
     pr
    0.28
    lette
    0.28
    çļĦ人æĿ¥è¯´
    0.27
    渥
    0.27
    æ»ij
    0.25
     fat
    0.25
    spl
    0.24
     Ryu
    0.24
    Activations Density 8.235%

    No Known Activations