© 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. 140564
    Prev
    Next
    INDEX
    Explanations

    Legal matters/past tense verbs

    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
    rad
    -0.30
    åı£å¤´
    -0.26
    .manual
    -0.25
    .rad
    -0.25
    ival
    -0.24
    硬件
    -0.24
    对æĪij
    -0.23
    éĻĤ
    -0.23
    æŀķ
    -0.23
    éĥħ
    -0.23
    POSITIVE LOGITS
     mong
    0.28
    IBLE
    0.27
     warrants
    0.27
    usher
    0.25
     ali
    0.25
    è§ij
    0.25
     Enumerable
    0.24
    StdString
    0.24
    注æĺİæĿ¥æºIJ
    0.24
    ustum
    0.23
    Activations Density 22.624%

    No Known Activations