© 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. 108526
    Prev
    Next
    INDEX
    Explanations

    King

    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
     WX
    -0.26
    ä¹Ŀé¾Ļ
    -0.26
    reich
    -0.26
     HA
    -0.25
    御
    -0.25
    åĪĴåĪĨ
    -0.24
    ulti
    -0.24
    stellen
    -0.23
    heits
    -0.23
    TRL
    -0.23
    POSITIVE LOGITS
     owners
    0.26
     paced
    0.26
    æ»Ķ
    0.25
    åĦ¿å¥³
    0.25
    ians
    0.25
    eree
    0.25
    çĪ±ä½ł
    0.24
    ateria
    0.23
    cats
    0.23
     Californ
    0.23
    Activations Density 41.468%

    No Known Activations