© 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. 6499
    Prev
    Next
    INDEX
    Explanations

    Abbreviations of titles

    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
    顽
    -0.28
    å°ĸ
    -0.26
    çĶŁäº§è®¾å¤ĩ
    -0.25
    æĬ¢åħĪ
    -0.25
    çļĦåѦçĶŁ
    -0.24
    ми
    -0.24
    çļĦ缸åħ³
    -0.24
    çļĦåŁºç¡Ģ
    -0.24
     mercy
    -0.24
     embeddings
    -0.23
    POSITIVE LOGITS
     Sultan
    0.30
    å°ģ建
    0.27
    onth
    0.27
    icate
    0.26
     Äijấu
    0.26
    arith
    0.25
    åıĹ害
    0.25
     UIManager
    0.24
    igious
    0.24
    esium
    0.24
    Activations Density 0.096%

    No Known Activations