© 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. 8328
    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
    è¿Ļ份
    -0.26
    otte
    -0.26
    å¥Ī
    -0.25
    éĤ£ä»½
    -0.25
     tá»Ŀ
    -0.24
    trieve
    -0.24
     Fat
    -0.24
    reeze
    -0.24
     sake
    -0.24
    å±ħ
    -0.24
    POSITIVE LOGITS
    主è¦ģä»İäºĭ
    0.29
    ulg
    0.27
     SG
    0.26
     BIND
    0.25
    ç£ķ
    0.25
    assoc
    0.25
     repeated
    0.25
    éĢīåĿĢ
    0.24
     Programs
    0.24
    æĪIJç«ĭäºİ
    0.24
    Activations Density 0.635%

    No Known Activations

    This feature has no known activations.