© 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. 62554
    Prev
    Next
    INDEX
    Explanations

    computer 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
    fly
    -0.26
    ä»ħ次äºİ
    -0.26
    屬æĸ¼
    -0.25
    flies
    -0.25
    ìĨį
    -0.25
    ãģ£ãģ¨
    -0.24
     appart
    -0.24
    /env
    -0.24
    enk
    -0.24
    Suit
    -0.24
    POSITIVE LOGITS
    DOMNode
    0.27
    _gc
    0.27
    oci
    0.26
    _received
    0.25
    orea
    0.25
    å¤ļå¤ļ
    0.25
    ()(
    0.25
    .snapshot
    0.24
    @mail
    0.24
    éģĩä¸Ĭ
    0.24
    Activations Density 34.203%

    No Known Activations