© 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. 22-TRANSCODER-HP
    7. 88776
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ńå°ıåŀĭ
    -0.30
    æłĩçļĦ
    -0.27
    æµħ
    -0.26
    ç¥ŀéĢļ
    -0.26
    åĵº
    -0.24
    proto
    -0.24
    æĹ·
    -0.24
    æĺŁæľŁ
    -0.24
     exc
    -0.23
     orientation
    -0.23
    POSITIVE LOGITS
    ä¸Ģçķª
    0.32
    ument
    0.26
    education
    0.24
    fcc
    0.24
    çī¡
    0.23
    uai
    0.23
    eor
    0.23
    fc
    0.23
    ucken
    0.23
    alm
    0.23
    Activations Density 0.000%

    No Known Activations