© 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. 111075
    Prev
    Next
    INDEX
    Explanations

    blog entries

    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
    æĥĬ人
    -0.28
    ç¼ĩ
    -0.27
    /native
    -0.26
    aly
    -0.25
    igital
    -0.25
    åģļ强
    -0.24
    èĤ¢ä½ĵ
    -0.24
    åħ³äºİæĪij们
    -0.24
     Marian
    -0.24
    æĹħ游èµĦæºIJ
    -0.23
    POSITIVE LOGITS
    hee
    0.30
    etu
    0.26
    è¿ĻæŶåĢĻ
    0.25
    åĵ¼
    0.25
     Immediately
    0.25
    icas
    0.24
    =settings
    0.24
    åħļä¸Ń央
    0.24
    acci
    0.24
    entai
    0.24
    Activations Density 0.047%

    No Known Activations