© 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. 140812
    Prev
    Next
    INDEX
    Explanations

    period

    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
    æĹ¶ä»£ä¸ŃåĽ½
    -0.31
    年代
    -0.28
    lier
    -0.26
    äºĴèģĶäºĴéĢļ
    -0.24
     mechanically
    -0.24
     gens
    -0.24
     Founder
    -0.24
    èĹ©
    -0.23
     Priv
    -0.23
    åIJĮå¹´
    -0.23
    POSITIVE LOGITS
    侧
    0.29
    èĴĮ
    0.28
    æħ¢
    0.28
    弥补
    0.26
    æ³¼
    0.25
    åŁĤ
    0.24
     CONST
    0.24
    blob
    0.24
    respond
    0.23
     remed
    0.23
    Activations Density 65.800%

    No Known Activations