© 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. 18-TRANSCODER-HP
    7. 88849
    Prev
    Next
    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Ĺ罪
    -0.29
    ä¸Ģè§Ĵ
    -0.26
    				↵				↵
    -0.25
    åijĬè¯ī她
    -0.24
     MediaTek
    -0.24
    è°Īè°Ī
    -0.24
    åĽ¢éķ¿
    -0.23
    olatile
    -0.23
    utters
    -0.23
     shooters
    -0.23
    POSITIVE LOGITS
    excel
    0.29
    intr
    0.29
    nda
    0.28
    craft
    0.27
     excel
    0.26
    为主ä½ĵ
    0.25
    echo
    0.24
     follows
    0.24
    ump
    0.23
     circuit
    0.23
    Activations Density 7.997%

    No Known Activations