© 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. 63352
    Prev
    Next
    INDEX
    Explanations

    Financial amounts and estimations

    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
    rove
    -0.26
    大éŨ
    -0.25
    vel
    -0.25
    åŃĸ
    -0.25
    éĥ¨éŨ
    -0.24
     viá»ĩn
    -0.24
    ä¸Ģ楼
    -0.24
    çªĿ
    -0.24
    iom
    -0.24
    UILTIN
    -0.24
    POSITIVE LOGITS
    Soup
    0.31
    ,next
    0.26
    erequisite
    0.24
     turquoise
    0.23
    ONDON
    0.23
    CHIP
    0.23
    erer
    0.23
    ALAR
    0.23
    ModelError
    0.22
    åºĨ幸
    0.22
    Activations Density 13.348%

    No Known Activations