© 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. 130784
    Prev
    Next
    INDEX
    Explanations

    7

    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
    ãĢģ
    -0.34
    åĴĮ
    -0.30
    à¹ģละ
    -0.29
     vÃł
    -0.28
     и
    -0.27
    è´¨éĩıåĴĮ
    -0.26
    .xml
    -0.26
    åħļåĴĮ
    -0.25
     ÙĪاÙĦ
    -0.25
     and
    -0.25
    POSITIVE LOGITS
    -built
    0.28
    plies
    0.26
    xic
    0.25
    åģľçķĻ
    0.25
    éĥijéĩį
    0.25
     kindly
    0.25
    gram
    0.24
    æĭīä¸ģ
    0.24
    æĸ¯åŁº
    0.24
    inning
    0.24
    Activations Density 51.066%

    No Known Activations