© 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. 130794
    Prev
    Next
    INDEX
    Explanations

    (

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ĥ
    -0.28
     cor
    -0.27
    çĪ±åĽ½
    -0.26
    éĤ£äºĽ
    -0.26
     Heart
    -0.26
     literally
    -0.26
    ç¡®åĪĩ
    -0.26
    å¿ĥè·³
    -0.25
    Heart
    -0.25
    odom
    -0.25
    POSITIVE LOGITS
    irst
    0.31
     Fountain
    0.25
    andes
    0.25
     Appliances
    0.25
    åħ¬ç¤º
    0.25
    /public
    0.24
    undos
    0.24
    à¸Ľà¸£à¸²à¸ģà¸ı
    0.24
    ä¸Ģ对
    0.24
     endpoint
    0.24
    Activations Density 5.037%

    No Known Activations