© 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. 142724
    Prev
    Next
    INDEX
    Explanations

    Technical systems and structures

    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
    çļĦå®ŀéĻħ
    -0.27
    çļĦé¢ľèī²
    -0.26
    æĹłæĦı
    -0.24
    æµĵ缩
    -0.24
    Bubble
    -0.24
    iens
    -0.24
     æ¸
    -0.24
    virt
    -0.24
    cit
    -0.23
    yl
    -0.23
    POSITIVE LOGITS
    _restrict
    0.26
     comprend
    0.26
    ä¹į
    0.24
    å®Ļ
    0.24
     Faul
    0.24
    æĪIJçĨŁçļĦ
    0.23
    ĪæĿĥ
    0.23
    èģĶç½ij
    0.23
    stime
    0.23
     Trib
    0.23
    Activations Density 33.979%

    No Known Activations