© 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. 129141
    Prev
    Next
    INDEX
    Explanations

    Code and symbols

    np_max-act · gemini-2.0-flash
    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
     seria
    -0.28
    ủng
    -0.27
    çīĮåŃIJ
    -0.26
     indeb
    -0.26
    åĦ¿
    -0.25
    /etc
    -0.24
    Slug
    -0.24
    SCALL
    -0.24
     *,↵
    -0.24
    ombine
    -0.24
    POSITIVE LOGITS
    eming
    0.31
     immediately
    0.29
    ä¹ĭ
    0.28
    s
    0.27
    {
    0.27
    çļĦéĥ¨åĪĨ
    0.27
    ãĥİ
    0.26
    äºİ
    0.26
    {})
    0.26
    β
    0.26
    Activations Density 0.138%

    No Known Activations