© 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. 30-TRANSCODER-HP
    7. 94989
    Prev
    Next
    INDEX
    Explanations

    clean

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éķ¬
    -0.28
     McGr
    -0.26
    å¥ĩçī¹
    -0.25
    è¿ģ
    -0.25
    InBackground
    -0.25
    hog
    -0.24
    宣
    -0.24
    ton
    -0.24
    ä¸Ģ个èģĮä¸ļ
    -0.24
    -bedroom
    -0.24
    POSITIVE LOGITS
     clean
    0.37
    å¹²åĩĢ
    0.34
    clean
    0.32
     cleaner
    0.32
    æ´ģåĩĢ
    0.32
     Clean
    0.30
    Clean
    0.28
    _clean
    0.28
    æ¸ħæ´ģ
    0.28
     pools
    0.27
    Activations Density 0.883%

    No Known Activations