© 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. 8879
    Prev
    Next
    INDEX
    Explanations

    Website functionality

    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
     tonight
    -0.29
    ocator
    -0.29
    Tonight
    -0.26
    ç¼¥
    -0.26
     dreaming
    -0.26
     Wo
    -0.25
    rypt
    -0.25
    åħľ
    -0.25
     wo
    -0.25
     Bucc
    -0.25
    POSITIVE LOGITS
    DMIN
    0.27
     witnesses
    0.27
     watchers
    0.26
     slows
    0.26
    åIJĦæĸ¹
    0.25
    isson
    0.25
    ä¸īæĸ¹
    0.25
     Pav
    0.24
    ä¸Ģå®ļçļĦ
    0.24
    opensource
    0.24
    Activations Density 0.008%

    No Known Activations