© 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. 62822
    Prev
    Next
    INDEX
    Explanations

    Zero

    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
    arily
    -0.32
    对éĺµ
    -0.30
    以èī²
    -0.29
    itos
    -0.28
    fans
    -0.28
     Fans
    -0.27
    梳
    -0.27
    woff
    -0.27
    Fans
    -0.27
     Affero
    -0.27
    POSITIVE LOGITS
    \Annotation
    0.27
    ihar
    0.26
    _document
    0.25
     sd
    0.25
     AAA
    0.25
     drop
    0.25
     NIC
    0.25
    çļĦè¦ģæ±Ĥ
    0.23
     xs
    0.23
    æł¸åĩĨ
    0.23
    Activations Density 0.959%

    No Known Activations