© 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. 64728
    Prev
    Next
    INDEX
    Explanations

    Questions, instructions, technical

    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
    chl
    -0.30
    OUR
    -0.28
     embarrassing
    -0.27
    ed
    -0.27
    yahoo
    -0.24
    éĢļ
    -0.24
    Spanish
    -0.24
    ÑĭÑĪ
    -0.24
    gan
    -0.24
    åĪĨæīĭ
    -0.24
    POSITIVE LOGITS
    çĻ¾äº¿
    0.28
    isten
    0.27
    striction
    0.26
    reten
    0.26
    åIJİ代
    0.26
    '](
    0.26
    使çĶ¨æĿĥ
    0.25
    çīĴ
    0.25
    rok
    0.25
    Toy
    0.25
    Activations Density 4.337%

    No Known Activations