© 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. 4765
    Prev
    Next
    INDEX
    Explanations

    is/are/when

    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
    gere
    -0.28
    tright
    -0.26
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.24
    æĹłåĬĽ
    -0.24
    ady
    -0.24
    etry
    -0.24
    éĺ¡
    -0.23
    ç´¯äºĨ
    -0.23
    大å°ı
    -0.23
    lessly
    -0.23
    POSITIVE LOGITS
    æŶéĹ´ä¸º
    0.28
     edible
    0.28
    omed
    0.26
    åĵ²
    0.26
    溶
    0.25
    ä¹ĭæīĢ
    0.25
    ::_
    0.24
    icus
    0.24
    ylon
    0.24
     nu
    0.24
    Activations Density 0.158%

    No Known Activations