© 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. 107815
    Prev
    Next
    INDEX
    Explanations

    text snippets

    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
    åĪ·
    -0.26
    edReader
    -0.25
    CD
    -0.25
    âį¨
    -0.25
    uest
    -0.24
    arLayout
    -0.24
     pardon
    -0.23
    rompt
    -0.23
    æ¿Ģ
    -0.23
    çī©ä½ĵ
    -0.23
    POSITIVE LOGITS
     infrastructure
    0.28
    аÑģÑģ
    0.27
    åŁºç¡Ģ设æĸ½
    0.26
     Cro
    0.25
    assandra
    0.25
    .Automation
    0.25
    æĪijåıijçİ°
    0.24
    å¹³åı°ä¸Ĭ
    0.23
    è¦ģèĢĥèĻij
    0.23
     vir
    0.23
    Activations Density 3.592%

    No Known Activations