© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149278
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    mere
    -0.29
    å¿ĹæĦ¿
    -0.26
    greg
    -0.25
     chÄĥm
    -0.24
    Infos
    -0.23
    åĸĻ
    -0.23
    icken
    -0.23
    onica
    -0.23
    IPS
    -0.23
    IFA
    -0.23
    POSITIVE LOGITS
    ä¸¥æł¼
    0.28
    ä¹ĭéģĵ
    0.27
    chers
    0.27
    è¿Ļ两年
    0.26
    æŃ²
    0.24
    è¿Ļåĩłå¹´
    0.24
    缮ãģ«
    0.24
    å²ģ
    0.24
    irty
    0.24
     topology
    0.23
    Activations Density 0.558%

    No Known Activations

    This feature has no known activations.