© 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. 129095
    Prev
    Next
    INDEX
    Explanations

    for

    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
    æĥħåĨµä¸ĭ
    -0.37
     times
    -0.33
     situations
    -0.30
     invest
    -0.30
    çļĦæĥħåĨµä¸ĭ
    -0.30
     scenario
    -0.29
     situation
    -0.29
    ç«
    -0.27
     scenarios
    -0.27
    æĿ¡ä»¶ä¸ĭ
    -0.27
    POSITIVE LOGITS
    ä»ĸä»¬åľ¨
    0.30
    edList
    0.28
    å¾Īæ·±
    0.26
    秧
    0.25
    ãĤĭãĤĤãģ®
    0.25
    ä»ĸ们æĺ¯
    0.24
    Ä°LÄ°
    0.24
    å¾Ĥ
    0.24
    PLIC
    0.24
    esis
    0.24
    Activations Density 0.034%

    No Known Activations