© 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. 88911
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    &amp
    -0.29
     try
    -0.28
     Baum
    -0.26
     diss
    -0.26
    antha
    -0.25
    ETHER
    -0.25
     invoked
    -0.25
    	Int
    -0.24
     viewer
    -0.24
     Bullet
    -0.24
    POSITIVE LOGITS
    кан
    0.30
    èĩªçĦ¶ç§ijåѦ
    0.26
    back
    0.25
    box
    0.25
    æ®ĸæ°ij
    0.25
    åħ¥ãĤĮ
    0.24
    zik
    0.24
    acky
    0.24
    éĢ¢
    0.24
    è¿İ
    0.23
    Activations Density 0.007%

    No Known Activations