© 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. 12-TRANSCODER-HP
    7. 22196
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĽŀæĥ³
    -0.28
    utive
    -0.28
    arch
    -0.27
    anness
    -0.27
    缸æ¯Ķä¹ĭä¸ĭ
    -0.27
    obel
    -0.26
    sumer
    -0.25
    istence
    -0.25
    MI
    -0.25
    设æĸ½å»ºè®¾
    -0.24
    POSITIVE LOGITS
    eyed
    0.37
    yre
    0.31
     advert
    0.26
     eyed
    0.26
    ighting
    0.26
    ÙĦÙĤ
    0.25
     strings
    0.25
    æł¼å¼ı
    0.24
    roat
    0.24
    ãĥ¯ãĤ¤
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.