© 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. 4686
    Prev
    Next
    INDEX
    Explanations

    Stop words, punctuation

    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
    åĪ°åºķ
    -0.28
    åĹ£
    -0.26
    еÑĤÑĮ
    -0.25
    æĬ¥
    -0.25
    æķĻæ¡Ī
    -0.24
    udio
    -0.23
     diminished
    -0.23
    æ£īèĬ±
    -0.23
    -trigger
    -0.23
    .abstract
    -0.23
    POSITIVE LOGITS
    姨
    0.28
     stole
    0.28
     umie
    0.27
    aches
    0.26
    èĢĥåľº
    0.25
    è¿ĺåĮħæĭ¬
    0.25
    ä¼ļéķ¿
    0.24
    @class
    0.24
     totalTime
    0.24
     parking
    0.24
    Activations Density 0.002%

    No Known Activations