© 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. 22-TRANSCODER-HP
    7. 86796
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĴĮå¹³
    -0.27
    uyến
    -0.26
    .rawValue
    -0.26
    æķ¬
    -0.26
    rop
    -0.26
    wnd
    -0.26
    éĻĨ
    -0.25
    éģĹæ¼ı
    -0.25
     grat
    -0.24
    alph
    -0.24
    POSITIVE LOGITS
    æ±Łæ·®
    0.25
     Easily
    0.25
    zilla
    0.24
    åĿļ飧
    0.24
    ä¾Ľç»Ļ
    0.24
    æĭ¶
    0.24
    åĿļ硬
    0.24
    BorderStyle
    0.24
     Sok
    0.24
    erson
    0.23
    Activations Density 0.019%

    No Known Activations