© 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. 63499
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
     Bureau
    -0.26
    éķ¿å¤§
    -0.26
     wrapped
    -0.25
     Charter
    -0.25
     last
    -0.24
    ä¸įåĪ°
    -0.24
    æĢ»éĩı
    -0.24
    åĿ¯
    -0.24
    ä¸įåİ»
    -0.24
    éĥ¨éķ¿
    -0.23
    POSITIVE LOGITS
    elijk
    0.27
    è¿ĻéĩĮçļĦ
    0.27
    ijkl
    0.26
    ç½Ħ
    0.24
    @ResponseBody
    0.24
     дал
    0.24
    é¹Į
    0.23
    ERRY
    0.23
    Ãłng
    0.23
    isbn
    0.23
    Activations Density 1.876%

    No Known Activations