© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8344
    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
    å°ı康社ä¼ļ
    -0.28
    åıijå±ķæĸ¹åIJij
    -0.26
    åĮĻ
    -0.25
    etak
    -0.24
    ä¸įéĢļ
    -0.24
    itect
    -0.24
    ours
    -0.24
    æºģ
    -0.23
    髹
    -0.23
    NG
    -0.23
    POSITIVE LOGITS
     pulses
    0.27
    è®°
    0.27
    æ´¾
    0.25
    è¿«
    0.25
     ép
    0.25
     Held
    0.23
    oz
    0.23
    åĪĨæĺİ
    0.23
     documentary
    0.23
    串
    0.23
    Activations Density 3.319%

    No Known Activations

    This feature has no known activations.