© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    -

    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
    çĭ¬ä¸ĢæĹłäºĮ
    -0.31
    éķij
    -0.26
    .locale
    -0.26
    é»»
    -0.25
     available
    -0.24
    [`
    -0.24
    å¢Ĵ
    -0.23
    REN
    -0.23
    ä¸ĩä¸Ģ
    -0.23
    opport
    -0.23
    POSITIVE LOGITS
    æ·»
    0.30
    è¿ŀç»Ń
    0.28
    æĮº
    0.26
    acking
    0.26
     adjunct
    0.26
    家åĬ¡
    0.26
    :right
    0.25
     æŀ
    0.25
    çļĦå°ı
    0.25
    åºı
    0.25
    Activations Density 0.008%

    No Known Activations