© 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. 108138
    Prev
    Next
    INDEX
    Explanations

    code

    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
    æľīä¸Ģç§į
    -0.33
     invented
    -0.31
     invent
    -0.30
    ç§įç±»
    -0.29
    åıijæĺİ
    -0.28
    æī¾åĪ°
    -0.28
    Silver
    -0.27
    ä¸įåIJĮçļĦ
    -0.26
    ãģıãģł
    -0.26
    sc
    -0.26
    POSITIVE LOGITS
    æĬķèµĦé¢Ŀ
    0.27
     MongoClient
    0.25
     til
    0.25
    ç´łè´¨æķĻèĤ²
    0.25
     Initialized
    0.25
    åĢ¾åIJij
    0.25
    _logged
    0.25
    ThreadId
    0.24
    .Container
    0.24
     Tits
    0.24
    Activations Density 55.745%

    No Known Activations