© 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. 23-TRANSCODER-HP
    7. 23649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    fuse
    -0.27
    vell
    -0.25
    åĪijäºĭæ¡Ī件
    -0.25
    æ½Ń
    -0.25
    ç«ĭãģ¦
    -0.25
    èİ«æĸ¯
    -0.24
    å¢ħ
    -0.24
    ç£ģ
    -0.24
    åĪĩ
    -0.24
     slack
    -0.23
    POSITIVE LOGITS
    ÑĨион
    0.31
    adopt
    0.29
    AQ
    0.27
    çļĦä»·æł¼
    0.25
     powers
    0.25
    aje
    0.25
     installs
    0.24
     merch
    0.23
    Dia
    0.23
    çĶ¨å¾®ä¿¡
    0.23
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.