© 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. 140553
    Prev
    Next
    INDEX
    Explanations

    Common, unspecific text

    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
     paranormal
    -0.26
    åIJĦ个æĸ¹éĿ¢
    -0.24
    ç§įç§į
    -0.24
     Paran
    -0.24
    XP
    -0.24
    ä¸ĩ象
    -0.23
    æķ·
    -0.23
    CTS
    -0.23
    owy
    -0.23
     Papers
    -0.23
    POSITIVE LOGITS
    chten
    0.25
     Turnbull
    0.24
     precious
    0.24
    pio
    0.24
    æĺŃ
    0.23
    .definition
    0.23
    chte
    0.23
    ulta
    0.23
    berry
    0.23
    ãĤ¿ãĤ¤
    0.23
    Activations Density 16.569%

    No Known Activations