© 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. 142672
    Prev
    Next
    INDEX
    Explanations

    Single digits

    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
    æµ®
    -0.25
    滤
    -0.25
    åłĨ
    -0.24
    è¿ĺ好
    -0.24
    ronics
    -0.24
    .DEFINE
    -0.24
     grades
    -0.23
    åĴĶ
    -0.23
    å¾ģ
    -0.23
    éķ¿
    -0.23
    POSITIVE LOGITS
    LEE
    0.28
    ustomed
    0.28
    tg
    0.27
    leurs
    0.25
    åłĤ
    0.25
    Bars
    0.24
    ä½ľé£İ
    0.24
    主è¦ģåİŁåĽł
    0.24
    æ´»è·ĥ
    0.24
    bars
    0.24
    Activations Density 11.527%

    No Known Activations