© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141891
    Prev
    Next
    INDEX
    Explanations

    Abbreviations, URLs, code, symbols

    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
    enheim
    -0.29
     Boeh
    -0.28
    lingen
    -0.27
    åĽ½å®¶æĪĺçķ¥
    -0.27
    usaha
    -0.27
    bows
    -0.26
    liches
    -0.26
    æŃĮè¯į
    -0.25
    icana
    -0.25
    /topics
    -0.25
    POSITIVE LOGITS
    èħ¾
    0.29
    åĮº
    0.28
    åIJĦåĮº
    0.28
     male
    0.28
     Male
    0.27
    åıĸ
    0.27
    åĮºåĨħ
    0.27
    sum
    0.26
    é³Į
    0.26
    æĥ³ä¸įåĪ°
    0.26
    Activations Density 3.982%

    No Known Activations