© 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. 141247
    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
     meld
    -0.28
    æĺ¯åIJ¦åŃĺåľ¨
    -0.28
    èIJ½åIJİ
    -0.28
     seperate
    -0.27
    æĸ°é²ľ
    -0.26
    iken
    -0.26
    èĩªåĪ¶
    -0.26
    IZER
    -0.26
    omens
    -0.25
    åħĥå®Ŀ
    -0.25
    POSITIVE LOGITS
    è¿Ļæĺ¯åĽłä¸º
    0.27
    renders
    0.26
     Amendment
    0.26
    avor
    0.26
     createContext
    0.26
    sched
    0.25
     Schedule
    0.25
    render
    0.25
    amu
    0.24
    çļĦåİŁåĽł
    0.24
    Activations Density 82.282%

    No Known Activations