© 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. 4872
    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
    裳
    -0.28
     Sight
    -0.27
    ain
    -0.25
    å¾Ĺåĩº
    -0.25
    NG
    -0.24
     harmonic
    -0.23
    ì°į
    -0.23
    æĬ¼
    -0.23
     common
    -0.23
     accommodation
    -0.23
    POSITIVE LOGITS
    æĪĸå¤ļæĪĸå°ij
    0.29
    ::↵↵
    0.28
    éĥ½æľīèĩªå·±
    0.27
    коп
    0.27
    çļĦè§Ĵèī²
    0.25
    ologically
    0.25
     reminds
    0.25
    pend
    0.25
    ita
    0.25
    åħ·æľīä¸Ģå®ļ
    0.25
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.