© 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. 107241
    Prev
    Next
    INDEX
    Explanations

    General english text

    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
    顾
    -0.27
    fl
    -0.26
    gue
    -0.26
    å½¼æѤ
    -0.25
    throp
    -0.25
     PROGMEM
    -0.24
    è¿«
    -0.24
    æ°ijæĹı
    -0.24
    åŃĹæ¯į
    -0.23
    æĴĩ
    -0.23
    POSITIVE LOGITS
     Weiner
    0.25
    PTY
    0.25
    ularity
    0.25
    éĢ²ãĤģ
    0.24
    çŃ¾çº¦
    0.24
    æĭĪ
    0.24
    ä¸įæĸŃå¢ŀ强
    0.24
    queues
    0.23
    /configuration
    0.23
    eln
    0.23
    Activations Density 18.337%

    No Known Activations