© 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. 19-TRANSCODER-HP
    7. 8583
    Prev
    Next
    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arrest
    -0.26
     comps
    -0.26
    ä¸Ńéĥ¨
    -0.25
     doi
    -0.24
    第ä¸ĢæŃ¥
    -0.24
    æĬĬè¿Ļ个
    -0.23
     Bowling
    -0.23
    è¿Ľåľº
    -0.23
     Nat
    -0.23
    <main
    -0.23
    POSITIVE LOGITS
    æѦåĬŁ
    0.24
    zend
    0.24
    çķĻä¸ĭäºĨ
    0.23
    ñe
    0.23
    稷
    0.23
    -equ
    0.23
    æ±
    0.23
    izen
    0.23
    鹤
    0.23
     TCL
    0.22
    Activations Density 0.010%

    No Known Activations