© 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. 130204
    Prev
    Next
    INDEX
    Explanations

    (

    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
    éĥ½ä¼ļæľī
    -0.32
    éĻ¤å¤ĸ
    -0.28
    pute
    -0.27
    labs
    -0.26
    à¹ģสà¸Ļ
    -0.26
    æĦĪ
    -0.26
    举æĬ¥
    -0.24
    åıijå¸ĥçļĦ
    -0.24
    ....↵
    -0.24
    缮
    -0.24
    POSITIVE LOGITS
    uja
    0.27
    åľºä¸Ĭ
    0.24
    weg
    0.24
     kop
    0.24
     OU
    0.24
    ëĭ´
    0.24
    &(
    0.24
    游æĪıä¸Ń
    0.24
    Öģ
    0.23
    åĨį
    0.23
    Activations Density 3.128%

    No Known Activations