© 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. 141205
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    æľĢç¾İçļĦ
    -0.32
    æľĢ好çļĦ
    -0.31
    Ĺı
    -0.29
    rex
    -0.27
    æľĢ主è¦ģçļĦ
    -0.27
    æľĢå¿«
    -0.27
    縳
    -0.27
    REATE
    -0.26
    æľĢ
    -0.26
    æľĢå¤ļçļĦ
    -0.26
    POSITIVE LOGITS
    mom
    0.26
    ãĥijãĥ¼
    0.25
    ä»İä¸Ń
    0.25
    çĹĽ
    0.24
    èµĭäºĪ
    0.24
    åĭĩ
    0.24
    侪
    0.24
    oined
    0.24
    aser
    0.23
    Moment
    0.23
    Activations Density 58.379%

    No Known Activations