© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 106819
    Prev
    Next
    INDEX
    Explanations

    1

    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
    Negative Logits
    åıªè¦ģ
    -0.29
    -haired
    -0.27
    åıªè¦ģæľī
    -0.26
    buster
    -0.25
    леÑĤ
    -0.24
    åįķåħĥ
    -0.24
    -end
    -0.24
    resses
    -0.23
    ments
    -0.23
    çĻ
    -0.23
    POSITIVE LOGITS
    {_
    0.28
    ">&#
    0.26
     besides
    0.25
    anke
    0.25
     @[
    0.24
    uve
    0.24
    ä¸įåIJ«
    0.24
    inue
    0.23
    oven
    0.23
    forge
    0.23
    Activations Density 18.982%

    No Known Activations