© 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. 20-TRANSCODER-HP
    7. 62576
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¾Ĺèµ·
    -0.29
    çİ°åľ¨å¾Īå¤ļ
    -0.29
    éĥ¨åī¯
    -0.28
    CTL
    -0.27
    ä¸į失
    -0.26
    æĿ¥è®¿
    -0.26
    =>"
    -0.25
     bearer
    -0.25
    acent
    -0.25
    çĽ¸ä¿¡å¤§å®¶
    -0.25
    POSITIVE LOGITS
    æĮijæĪĺ
    0.27
     min
    0.26
     marginal
    0.25
     Rach
    0.25
    	min
    0.25
    ager
    0.24
    æ´¾
    0.23
     bids
    0.23
     less
    0.23
     ger
    0.23
    Activations Density 19.373%

    No Known Activations