© 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. 5161
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
     hứng
    -0.28
    èIJ½åĪ°
    -0.27
     TSRMLS
    -0.27
    ä¹İ
    -0.26
    ekt
    -0.26
    çļĦ羣å®ŀæĢ§
    -0.25
    è¬ĩ
    -0.24
    æł¼å±Ģ
    -0.24
    å¸ľ
    -0.24
    åĪĨéĴŁå·¦åı³
    -0.24
    POSITIVE LOGITS
     alternative
    0.31
    alternative
    0.28
     alternatively
    0.28
     alternate
    0.27
     deposition
    0.27
    plex
    0.26
    aving
    0.26
    æĢĢåŃķ
    0.26
     cost
    0.25
     blown
    0.25
    Activations Density 0.009%

    No Known Activations