© 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. 141626
    Prev
    Next
    INDEX
    Explanations

    code and web content

    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
     tapped
    -0.28
    缸æ¯Ķ
    -0.28
    ApplicationContext
    -0.25
    iena
    -0.25
    ino
    -0.25
     quo
    -0.24
    æī¿æİ¥
    -0.24
    èĢĥ
    -0.24
    ä¹ĭéĹ´
    -0.24
     czÄĻsto
    -0.24
    POSITIVE LOGITS
    æł¹æį®ä¸įåIJĮ
    0.33
     universal
    0.33
     ÑĥнивеÑĢÑģ
    0.30
    universal
    0.30
    (platform
    0.29
     depending
    0.29
    Depending
    0.29
     jurisdictions
    0.29
    depending
    0.29
    æµ·åĨħå¤ĸ
    0.28
    Activations Density 71.616%

    No Known Activations