© 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. 4733
    Prev
    Next
    INDEX
    Explanations

    Introductions and references

    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
    ejs
    -0.25
    èĽĽ
    -0.25
    iar
    -0.25
    aben
    -0.24
    IONS
    -0.24
    ValueCollection
    -0.24
    æ¸ħåĩī
    -0.24
    éħ±æ²¹
    -0.24
    inia
    -0.23
    icks
    -0.23
    POSITIVE LOGITS
    win
    0.26
    éĿĽ
    0.25
    æģ¯
    0.24
    antic
    0.24
    æģĴ
    0.24
     meaning
    0.24
    design
    0.24
     kort
    0.24
    è¯ķ
    0.23
     ÄijÃŃch
    0.23
    Activations Density 0.060%

    No Known Activations