© 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. 130612
    Prev
    Next
    INDEX
    Explanations

    has

    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
    她æĺ¯
    -0.25
    ä»ĸ们æĺ¯
    -0.25
    ä»ĸæĺ¯
    -0.25
    两边
    -0.25
    ANGER
    -0.24
    æĺ¯çĶ¨æĿ¥
    -0.24
    åı¦ä¸Ģè¾¹
    -0.24
    ****↵
    -0.24
    coder
    -0.24
    姥
    -0.24
    POSITIVE LOGITS
     unfinished
    0.30
    tle
    0.26
    ifiable
    0.26
    æŀľ
    0.25
     вÑĭп
    0.25
    ivet
    0.24
     Tao
    0.24
     dj
    0.24
    tractive
    0.24
    .fields
    0.24
    Activations Density 12.397%

    No Known Activations