© 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. 129818
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical writing

    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
    äºİæѤ
    -0.34
    ç»ĻäºĨæĪij
    -0.30
    åľ¨è¿ĻéĩĮ
    -0.29
    ä½Ĩæĺ¯å¯¹äºİ
    -0.28
    å°¤åħ¶æĺ¯åľ¨
    -0.27
    对äºİæĪij们
    -0.27
     particul
    -0.26
    ä»Ĭ
    -0.26
    å°¤åħ¶æĺ¯
    -0.26
    åľ¨ä»Ĭå¹´
    -0.26
    POSITIVE LOGITS
     fly
    0.27
    泪
    0.26
    ỵ
    0.25
    arguments
    0.24
     bet
    0.24
    adh
    0.24
    izz
    0.24
    éļıæŶ
    0.24
    ulture
    0.24
     vö
    0.23
    Activations Density 63.932%

    No Known Activations