© 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. 108342
    Prev
    Next
    INDEX
    Explanations

    Code/URLs

    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
    iversity
    -0.28
     complex
    -0.28
    çĶŁåŃĺ
    -0.27
     bri
    -0.27
     Complex
    -0.27
    complex
    -0.26
    Complex
    -0.25
     ce
    -0.25
     liv
    -0.25
    -open
    -0.25
    POSITIVE LOGITS
    ä¸Ģå¤ľ
    0.24
    éģĹ迹
    0.24
     Hamp
    0.24
     nghiá»ĩm
    0.24
     thừa
    0.24
    essoa
    0.23
     weekly
    0.23
    pcodes
    0.23
    æ¶Īè´¹èĢħçļĦ
    0.23
    诸侯
    0.23
    Activations Density 0.381%

    No Known Activations