© 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. 4892
    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
     mole
    -0.29
     ÑĢеж
    -0.27
     Tank
    -0.27
    åĩ»æĿĢ
    -0.25
    æľ¬åľŁ
    -0.25
    æĿ¼
    -0.24
     ÑģÑĤоÑĢ
    -0.24
    OLF
    -0.24
     mắc
    -0.24
     boarding
    -0.23
    POSITIVE LOGITS
    -offset
    0.28
    å®ĺ
    0.28
    客
    0.27
     gep
    0.27
     Rather
    0.25
    -exp
    0.25
    åįļè§Īä¼ļ
    0.24
    骨æŀ¶
    0.24
    eut
    0.24
    éĽ¯
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.