© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Props
    -0.26
    DESC
    -0.24
    sch
    -0.24
    inia
    -0.24
    auga
    -0.24
    iate
    -0.23
    iasi
    -0.23
    æķ°éĩı
    -0.23
    it
    -0.22
    éĺŁåijĺ
    -0.22
    POSITIVE LOGITS
    笼
    0.28
     typedef
    0.28
    åĪ³
    0.26
    èĥ½åģļåĪ°
    0.24
    æķĪ
    0.24
    Īĺ
    0.24
    ä¸ĢæĿ¡é¾Ļ
    0.24
     subtree
    0.23
     crib
    0.23
    æīįè¡Į
    0.23
    Activations Density 0.470%

    No Known Activations

    This feature has no known activations.