© 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. 141919
    Prev
    Next
    INDEX
    Explanations

    mixed code and 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
    çºł
    -0.26
    åŃļ
    -0.26
    äººåľ¨
    -0.26
    IZER
    -0.26
    Instance
    -0.26
    clo
    -0.24
     clic
    -0.24
     voi
    -0.24
    OLF
    -0.24
    ÑĢон
    -0.24
    POSITIVE LOGITS
    ä¸įçĽ¸ä¿¡
    0.26
     birth
    0.25
    åľ°æĸ¹
    0.25
    åĩºçĶŁ
    0.25
    åıĹçĽĬ
    0.24
    ascade
    0.24
    太平æ´ĭ
    0.23
    è¯ŀçĶŁ
    0.23
     Buckingham
    0.23
    åħīéĺ´
    0.23
    Activations Density 11.190%

    No Known Activations