© 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. 4714
    Prev
    Next
    INDEX
    Explanations

    code and technical strings

    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
    æ±Ŀ
    -0.26
    pipe
    -0.26
    egral
    -0.26
    æĮ
    -0.25
    åłª
    -0.24
    bil
    -0.24
    æŀĦ
    -0.24
    -lite
    -0.24
    æŁł
    -0.24
     asks
    -0.24
    POSITIVE LOGITS
    æ¸Ĭ
    0.26
    ialized
    0.25
    ặt
    0.25
    aea
    0.25
    ida
    0.24
    ÑģÑħ
    0.24
    æijĺè¦ģ
    0.24
    èĢĮéĿŀ
    0.24
    emap
    0.23
     deserved
    0.23
    Activations Density 0.017%

    No Known Activations