© 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. 140603
    Prev
    Next
    INDEX
    Explanations

    code/documentation

    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
    ,cp
    -0.28
    .bp
    -0.26
    ä¸ĩäºĭ
    -0.26
    ittance
    -0.24
    iances
    -0.24
    alled
    -0.24
    -bal
    -0.23
    ë´ĩ
    -0.23
     nuts
    -0.23
    ä¸ĩåĪĨ
    -0.23
    POSITIVE LOGITS
    å²Ľ
    0.30
    ÑĩÑĥ
    0.27
     tail
    0.26
     electromagnetic
    0.26
    乡
    0.26
    ×ķ×Ĺ
    0.25
    ailing
    0.25
     mar
    0.25
    obi
    0.25
    دÙĪ
    0.25
    Activations Density 5.913%

    No Known Activations