© 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. 4968
    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
    羣æŃ£åģļåĪ°
    -0.28
    æĻķ
    -0.28
    isode
    -0.27
    ç´ł
    -0.27
    æ´»è·ĥ
    -0.25
    æĿ¿
    -0.24
    variation
    -0.24
    emonic
    -0.23
     SAL
    -0.23
     pytest
    -0.23
    POSITIVE LOGITS
     adm
    0.26
    溲
    0.26
    ushing
    0.26
    erator
    0.25
    ắc
    0.24
    asper
    0.23
    æİĴåIJį第ä¸Ģ
    0.23
     undef
    0.23
    .cloudflare
    0.23
    +)\
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.