© 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. 6518
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Character
    -0.25
    æŃ£ç¡®çļĦ
    -0.24
    åı£æ°Ķ
    -0.24
    bil
    -0.24
    b
    -0.24
    好人
    -0.23
     Character
    -0.23
    çĮ®è¡Ģ
    -0.23
     Outer
    -0.23
    thon
    -0.23
    POSITIVE LOGITS
     ESP
    0.28
    ESP
    0.28
    IFA
    0.26
     unc
    0.26
    å®£ä¼łæķĻèĤ²
    0.25
     Lanc
    0.25
    ÙĦÙħ
    0.24
    à¤Ľ
    0.23
    æĸ°éĹ»ç½ij
    0.23
     launches
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.