© 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. 62660
    Prev
    Next
    INDEX
    Explanations

    with

    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
    subset
    -0.27
     Northwestern
    -0.25
    DER
    -0.24
    _derivative
    -0.24
    iem
    -0.24
    以çĤº
    -0.24
    åħ³äºİæĪij们
    -0.24
    kor
    -0.24
    ä¸įçĽ¸ä¿¡
    -0.23
    ographer
    -0.23
    POSITIVE LOGITS
    ëłģ
    0.32
    强
    0.28
    ä¸ĺ
    0.28
    çĽĺ
    0.27
    æ³ī
    0.26
    alue
    0.26
    åī¥
    0.25
    涧
    0.25
     Lowell
    0.24
    ipse
    0.24
    Activations Density 17.163%

    No Known Activations