© 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. 62634
    Prev
    Next
    INDEX
    Explanations

    is was

    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
    çĻ»
    -0.27
     trophies
    -0.26
     myths
    -0.26
     memes
    -0.26
    éĥ¨éĥ¨éķ¿
    -0.25
    çīĪæĿĥå½Ĵ
    -0.25
     legends
    -0.25
    underline
    -0.25
    .getHeader
    -0.25
     exp
    -0.25
    POSITIVE LOGITS
    Phys
    0.29
     Phys
    0.28
    .Now
    0.24
    ì§ĵ
    0.23
    mploy
    0.23
    onomous
    0.23
     phys
    0.23
    å¦Ĥä»Ĭ
    0.23
    :].
    0.23
    éĤ£æŶ
    0.22
    Activations Density 23.786%

    No Known Activations