© 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. 8947
    Prev
    Next
    INDEX
    Explanations

    text

    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
    æģ°æģ°
    -0.26
    erness
    -0.26
    ccoli
    -0.25
     Collision
    -0.23
    pcodes
    -0.22
    åı£ä¸Ń
    -0.22
    æ¸ħéĨĴ
    -0.22
    ä»Ĭ天
    -0.21
    çªģåĩº
    -0.21
    ä¸įäºĨ解
    -0.21
    POSITIVE LOGITS
    istical
    0.28
    ural
    0.26
     optionally
    0.24
     dang
    0.24
    ikel
    0.24
    æĦıä¹īä¸ĬçļĦ
    0.23
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.23
     slate
    0.22
    sched
    0.22
    åĭĻ
    0.22
    Activations Density 1.841%

    No Known Activations