© 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. 64676
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    å®Į
    -0.27
    çľ¼éĩĮ
    -0.27
    éĽ¨æ°´
    -0.25
    æ°Ķ
    -0.24
    antee
    -0.24
    æĻ¦
    -0.24
     leaked
    -0.24
     dil
    -0.24
    atrice
    -0.23
     element
    -0.23
    POSITIVE LOGITS
    BED
    0.27
    aron
    0.27
    (ord
    0.26
    çľĭä¸Ģçľĭ
    0.26
    oked
    0.26
    没æľīæĥ³åĪ°
    0.26
    stood
    0.26
    major
    0.25
    bery
    0.25
    icz
    0.24
    Activations Density 1.258%

    No Known Activations